© 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. 11-RESID-POST-AA
    11. 62162
    Prev
    Next
    INDEX
    Explanations

    bits

    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
     hailed
    -0.07
    妊
    -0.07
    短时间内
    -0.07
     grap
    -0.07
    内陆
    -0.07
    フラ
    -0.07
     REPL
    -0.07
    ขาด
    -0.07
     underst
    -0.07
     thổ
    -0.07
    POSITIVE LOGITS
    YC
    0.07
    device
    0.07
    ceso
    0.07
     enemy
    0.07
     Houses
    0.07
    енный
    0.07
     Immediately
    0.07
    _random
    0.07
    Alias
    0.07
    ony
    0.07
    Activations Density 0.016%

    No Known Activations