© 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. 30360
    Prev
    Next
    INDEX
    Explanations

    night time

    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
    (poly
    -0.07
    改
    -0.07
     Devils
    -0.07
    _TEMPLATE
    -0.07
     cảnh
    -0.07
     đảo
    -0.07
    젱
    -0.07
    턴
    -0.07
    넙
    -0.06
    즁
    -0.06
    POSITIVE LOGITS
    葳
    0.08
    	the
    0.07
     watchdog
    0.07
     archaeological
    0.07
    ながら
    0.07
    (weight
    0.07
    .getHeader
    0.07
    )findViewById
    0.07
     una
    0.07
     embarrassing
    0.06
    Activations Density 0.008%

    No Known Activations