© 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. 40766
    Prev
    Next
    INDEX
    Explanations

    multimedia

    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
     remind
    -0.07
    @param
    -0.07
     shampoo
    -0.06
    @↵
    -0.06
    &page
    -0.06
     конт
    -0.06
    ahoo
    -0.06
     ;;^
    -0.06
    .ctrl
    -0.06
     tarn
    -0.06
    POSITIVE LOGITS
    .SharedPreferences
    0.07
    executable
    0.07
    vable
    0.07
    Drawing
    0.07
    responses
    0.07
    .StretchImage
    0.07
    送往
    0.07
    伏
    0.06
    匣
    0.06
    不行
    0.06
    Activations Density 0.002%

    No Known Activations