© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130063
    Prev
    Next
    INDEX
    Explanations

    threat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŃĺ
    -0.26
    踮
    -0.25
    ä»ĸä¹Ł
    -0.24
     sû
    -0.24
    æŃ¤é¡¹
    -0.23
    åĮ¡
    -0.23
    æĻ®æĥł
    -0.23
    ระà¸ļ
    -0.23
    hra
    -0.23
     MIS
    -0.23
    POSITIVE LOGITS
    amoto
    0.28
    ned
    0.28
     zw
    0.24
    tableName
    0.23
    ods
    0.23
    jer
    0.23
    substr
    0.23
    éĩijåŃĹ
    0.23
     Blvd
    0.23
    åİ©
    0.23
    Activations Density 0.009%

    No Known Activations