© 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. 22004
    Prev
    Next
    INDEX
    Explanations

    cod

    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
    既
    -0.07
    试验
    -0.07
    笑声
    -0.07
    唉
    -0.07
    Bruce
    -0.07
    Sr
    -0.07
     Mir
    -0.06
    صحاب
    -0.06
     CS
    -0.06
    想念
    -0.06
    POSITIVE LOGITS
     Yahoo
    0.07
     JObject
    0.07
    _plate
    0.06
     Wash
    0.06
     Pills
    0.06
    湯
    0.06
     Yug
    0.06
    健康产业
    0.06
     hol
    0.06
     Close
    0.06
    Activations Density 0.004%

    No Known Activations