© 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. 7-RESID-POST-AA
    11. 42156
    Prev
    Next
    INDEX
    Explanations

    is/his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    זן
    -0.07
    اسرائيل
    -0.07
    🎱
    -0.07
    发改委
    -0.07
     Harley
    -0.07
     MSR
    -0.07
    hoe
    -0.07
     השנה
    -0.06
    ATEST
    -0.06
    DATES
    -0.06
    POSITIVE LOGITS
     His
    0.09
     diapers
    0.09
    argins
    0.07
    等各种
    0.07
    վ
    0.07
    Known
    0.07
    =img
    0.07
    nable
    0.07
    $client
    0.07
    Metrics
    0.07
    Activations Density 0.036%

    No Known Activations