© 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. 112454
    Prev
    Next
    INDEX
    Explanations

    Trad

    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
    举
    -0.28
    neas
    -0.26
    è½½
    -0.25
    laus
    -0.24
    gary
    -0.24
    uos
    -0.24
    ä¸Ģè§Ĵ
    -0.24
    常æĢģ
    -0.24
    spot
    -0.23
    mö
    -0.23
    POSITIVE LOGITS
     economy
    0.26
    å¸ĮæľĽèĩªå·±
    0.25
    usher
    0.25
    è¿Ļæĺ¯æĪij
    0.25
    ErrMsg
    0.24
     /*!
    0.24
    æĺ¯æĪijåĽ½
    0.24
    è¿Ļ件äºĭæĥħ
    0.24
    æŃ³
    0.23
    /*!↵
    0.23
    Activations Density 0.016%

    No Known Activations