© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7738
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     كانوا
    -0.07
     romance
    -0.07
     subtract
    -0.07
    女子
    -0.07
     فلا
    -0.07
    以便
    -0.07
    といえば
    -0.07
    _handle
    -0.07
     свою
    -0.07
    -posts
    -0.06
    POSITIVE LOGITS
     lạc
    0.07
    aar
    0.07
    (Project
    0.07
    Lic
    0.07
    var
    0.07
     Proud
    0.06
     Permit
    0.06
    =ax
    0.06
    ector
    0.06
    ött
    0.06
    Activations Density 0.146%

    No Known Activations