© 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. 111195
    Prev
    Next
    INDEX
    Explanations

    Objects

    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
    -China
    -0.07
    慮
    -0.07
    贯通
    -0.07
    tern
    -0.07
    題
    -0.07
    ﺴ
    -0.07
    ==
    -0.07
    INES
    -0.06
     sáng
    -0.06
    בס
    -0.06
    POSITIVE LOGITS
    predictions
    0.07
    /portfolio
    0.07
     מע
    0.07
     Ezek
    0.07
    OffsetTable
    0.07
    特价
    0.07
    肉
    0.06
    "];
↵
    0.06
    二百
    0.06
    На
    0.06
    Activations Density 0.001%

    No Known Activations