Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 25941
    Prev
    Next
    INDEX
    Explanations

    Chemical solvents

    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
     happening
    -0.08
    不适合
    -0.08
    巧克
    -0.07
    比例
    -0.07
     strategy
    -0.07
    基本信息
    -0.07
     posed
    -0.06
    챠
    -0.06
    毫米
    -0.06
    未知
    -0.06
    POSITIVE LOGITS
    irm
    0.07
     Baltimore
    0.07
    (lower
    0.07
    ADM
    0.07
    而去
    0.06
     Finally
    0.06
    د
    0.06
     input
    0.06
    ,SLOT
    0.06
    .DataTable
    0.06
    Activations Density 0.044%

    No Known Activations