© 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. 29792
    Prev
    Next
    INDEX
    Explanations

    :

    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
    uz
    -0.07
    urther
    -0.07
    づ
    -0.07
     ";
    ↵
    -0.07
    -pound
    -0.07
     snug
    -0.07
     Odds
    -0.06
    까지
    -0.06
     כולל
    -0.06
     PICK
    -0.06
    POSITIVE LOGITS
     bytecode
    0.08
    iping
    0.07
    言行
    0.07
    踩
    0.07
    HIGH
    0.07
     вли
    0.07
    사업
    0.06
    Bs
    0.06
     нашем
    0.06
    _crypto
    0.06
    Activations Density 0.002%

    No Known Activations