© 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. 15-RESID-POST-AA
    11. 12782
    Prev
    Next
    INDEX
    Explanations

    quotations in news articles

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drivers
    -0.08
     Zig
    -0.07
    дон
    -0.07
    揪
    -0.07
    꾈
    -0.07
    anky
    -0.07
    持股
    -0.07
    	seq
    -0.07
     commissions
    -0.06
    deer
    -0.06
    POSITIVE LOGITS
     ремонт
    0.07
    ела
    0.07
    ➔
    0.07
    ulture
    0.07
    成熟的
    0.07
    uture
    0.07
    ود
    0.07
    apper
    0.07
    出了
    0.06
    ès
    0.06
    Activations Density 0.019%

    No Known Activations