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

    Neuronpedia

    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. 57648
    Prev
    Next
    INDEX
    Explanations

    C++ code

    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
    葖
    -0.07
    ernes
    -0.07
    延伸
    -0.07
     complains
    -0.07
    __).
    -0.07
    手感
    -0.06
    SSL
    -0.06
    kończył
    -0.06
    .chomp
    -0.06
     philosophy
    -0.06
    POSITIVE LOGITS
     alex
    0.07
     Québec
    0.07
    ꦩ
    0.07
     Inventory
    0.06
     indicator
    0.06
    نحن
    0.06
    尼克
    0.06
    ิต
    0.06
     Maker
    0.06
    anagan
    0.06
    Activations Density 0.003%

    No Known Activations