© 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. 15-RESID-POST-AA
    11. 1167
    Prev
    Next
    INDEX
    Explanations

    disclaimers and legal jargon

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (keys
    -0.07
     examine
    -0.07
    言
    -0.07
    记
    -0.07
    索
    -0.06
    /Private
    -0.06
     Johns
    -0.06
    ủ
    -0.06
    失效
    -0.06
    ǽ
    -0.06
    POSITIVE LOGITS
     cortex
    0.07
    %");↵
    0.07
    贩
    0.07
    objectId
    0.07
    追捧
    0.07
    总公司
    0.07
     ArrayList
    0.07
    eceği
    0.06
     DIV
    0.06
    &);↵↵
    0.06
    Activations Density 0.014%

    No Known Activations