© 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. 13443
    Prev
    Next
    INDEX
    Explanations

    silane

    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
    낌
    -0.07
    CppGeneric
    -0.07
    ernote
    -0.07
    marsh
    -0.07
    HX
    -0.07
    🥂
    -0.07
    “If
    -0.07
     TRADE
    -0.07
     рейт
    -0.07
    蝻
    -0.07
    POSITIVE LOGITS
     displayed
    0.07
     Database
    0.07
     magazines
    0.07
     IMAGE
    0.07
    _contract
    0.07
    oko
    0.06
    _hit
    0.06
     Handlers
    0.06
    Instance
    0.06
     компания
    0.06
    Activations Density 0.006%

    No Known Activations