© 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. 85959
    Prev
    Next
    INDEX
    Explanations

    by

    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
     режим
    -0.07
    energy
    -0.07
    人间
    -0.07
    clidean
    -0.07
    丰胸
    -0.07
    Repeat
    -0.07
     Ling
    -0.07
     Harmony
    -0.07
     visc
    -0.07
     vẽ
    -0.07
    POSITIVE LOGITS
    上司
    0.08
     OutputStream
    0.08
    شور
    0.08
    counter
    0.07
     survivors
    0.07
     columnHeader
    0.07
     advisor
    0.07
     לקוח
    0.06
     survivor
    0.06
    cd
    0.06
    Activations Density 0.002%

    No Known Activations