© 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. 49305
    Prev
    Next
    INDEX
    Explanations

    area

    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
     Throne
    -0.08
     dissolve
    -0.07
    Kyle
    -0.07
     Diane
    -0.07
    中东
    -0.07
     Tucker
    -0.07
     зим
    -0.07
    Doug
    -0.06
    Ryan
    -0.06
    克里斯
    -0.06
    POSITIVE LOGITS
    בקש
    0.07
    _userid
    0.07
     На
    0.07
    ꦮ
    0.06
    耖
    0.06
     onViewCreated
    0.06
     Basket
    0.06
     маст
    0.06
    ,Object
    0.06
    tów
    0.06
    Activations Density 0.017%

    No Known Activations