© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 115409
    Prev
    Next
    INDEX
    Explanations

    C# dependency injection 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_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
    Chi
    -0.07
     Nut
    -0.07
    _RDONLY
    -0.06
     Salt
    -0.06
    粼
    -0.06
    GT
    -0.06
    -negative
    -0.06
     Sent
    -0.06
    InputStream
    -0.06
     salt
    -0.06
    POSITIVE LOGITS
    (tp
    0.07
     subst
    0.07
    ומה
    0.07
    shared
    0.07
     teamwork
    0.07
    (rd
    0.07
    раз
    0.07
    ?option
    0.07
    _atom
    0.06
    lóg
    0.06
    Activations Density 0.004%

    No Known Activations