© 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. 113329
    Prev
    Next
    INDEX
    Explanations

    appealed/appeals

    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
     Neb
    -0.07
     Blogs
    -0.07
     lethal
    -0.07
    ולים
    -0.07
    _VERTEX
    -0.07
    ﺀ
    -0.07
    ↲
    -0.07
     tok
    -0.07
    تحمل
    -0.06
    nThe
    -0.06
    POSITIVE LOGITS
    identified
    0.08
     ///</
    0.07
     deriving
    0.07
    #$
    0.07
     ${↵
    0.07
    ':'
    0.06
    建�
    0.06
    .Volume
    0.06
    #"
    0.06
    ensure
    0.06
    Activations Density 0.004%

    No Known Activations