© 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 EvalsExportsAPI 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. 79778
    Prev
    Next
    INDEX
    Explanations

    crime news

    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
    扩建
    -0.07
    哲
    -0.07
    聞
    -0.07
     rendez
    -0.06
    롬
    -0.06
     CB
    -0.06
    &B
    -0.06
    .amazon
    -0.06
    ʑ
    -0.06
     deficient
    -0.06
    POSITIVE LOGITS
    Driving
    0.07
    (ms
    0.06
     втор
    0.06
    正好
    0.06
    donnees
    0.06
    licity
    0.06
    中途
    0.06
    (weight
    0.06
    (bucket
    0.06
     occurring
    0.06
    Activations Density 0.045%

    No Known Activations