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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48408
    Prev
    Next
    INDEX
    Explanations

    EN

    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
    改良
    -0.07
     startled
    -0.07
     UITapGestureRecognizer
    -0.07
    改装
    -0.07
     פרי
    -0.07
     luxurious
    -0.07
    (FLAGS
    -0.07
     Imm
    -0.06
    潍
    -0.06
     Fit
    -0.06
    POSITIVE LOGITS
    OBJECT
    0.07
    ของเรา
    0.07
    uces
    0.07
     occas
    0.07
    ename
    0.07
    لاق
    0.07
    _singleton
    0.06
    单
    0.06
     отнош
    0.06
     بش
    0.06
    Activations Density 0.000%

    No Known Activations