© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 127038
    Prev
    Next
    INDEX
    Explanations

    organizations and companies

    np_max-act · gemini-2.0-flash

    mentions of organizations, companies, or formal institutions (proper names of entities).

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _resume
    -0.08
    蔈
    -0.07
     validated
    -0.07
    (input
    -0.07
     Sai
    -0.07
    ​↵↵
    -0.07
     SAME
    -0.07
     العملات
    -0.07
    说道
    -0.07
    招生
    -0.07
    POSITIVE LOGITS
     mindful
    0.08
    ผสม
    0.08
    党组成员
    0.07
     unaware
    0.07
     >(
    0.07
    .contains
    0.07
     because
    0.07
    尴
    0.07
    двига
    0.07
    חוו
    0.06
    Activations Density 3.713%

    No Known Activations