© 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. 129354
    Prev
    Next
    INDEX
    Explanations

    to

    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
    的身影
    -0.07
     الجزائ
    -0.07
    ﺕ
    -0.07
    entimes
    -0.07
    勘
    -0.07
    [t
    -0.07
    _US
    -0.06
    .'''↵
    -0.06
    麋
    -0.06
    itulo
    -0.06
    POSITIVE LOGITS
     boarded
    0.08
     productions
    0.08
     sürü
    0.08
     cooked
    0.07
    أصول
    0.07
    Bone
    0.07
     Converted
    0.07
     unanimous
    0.07
     committing
    0.07
    anything
    0.07
    Activations Density 0.003%

    No Known Activations