© 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. 19-RESID-POST-AA
    11. 74053
    Prev
    Next
    INDEX
    Explanations

    sub

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    dığını
    -0.08
    斗志
    -0.07
     يقوم
    -0.07
     Tâm
    -0.07
    让消费者
    -0.07
     ved
    -0.07
     Message
    -0.07
     gettimeofday
    -0.07
    さんに
    -0.07
     söyle
    -0.07
    POSITIVE LOGITS
    -human
    0.08
    :^(
    0.08
    figures
    0.07
    选项
    0.07
     exile
    0.07
    ]*(
    0.07
    -priced
    0.07
     IEnumerator
    0.07
    overs
    0.06
     forgotten
    0.06
    Activations Density 0.000%

    No Known Activations