© 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. 42465
    Prev
    Next
    INDEX
    Explanations

    have

    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
    ご紹介
    -0.07
    innitus
    -0.07
    不代表
    -0.07
     parchment
    -0.07
     swords
    -0.07
    .rs
    -0.07
     genesis
    -0.07
     disput
    -0.07
    acements
    -0.06
     Cornwall
    -0.06
    POSITIVE LOGITS
     quem
    0.07
    ሞ
    0.07
    찹
    0.07
    𝕙
    0.07
    𝓒
    0.07
    giatan
    0.07
    _shortcode
    0.07
    ﲰ
    0.06
    著作權
    0.06
    ))){↵
    0.06
    Activations Density 0.054%

    No Known Activations