© 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. 11-RESID-POST-AA
    6. 25422
    Prev
    Next
    INDEX
    Explanations

    .g

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    butt
    -0.08
    스트
    -0.08
     around
    -0.08
    unched
    -0.07
    ından
    -0.07
    ists
    -0.07
    شركة
    -0.07
     those
    -0.07
    aciente
    -0.07
    _list
    -0.07
    POSITIVE LOGITS
    RAW
    0.07
    ENDED
    0.07
    	REG
    0.07
     Gaw
    0.07
     Câm
    0.07
    (local
    0.07
    产学
    0.07
    볼
    0.07
    ꝛ
    0.07
    ⟱
    0.07
    Activations Density 0.018%

    No Known Activations