© 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. 31-TRANSCODER-HP
    7. 18661
    Prev
    Next
    INDEX
    Explanations

    of/from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asympt
    -0.29
     fee
    -0.26
     detections
    -0.24
    åĩłä½į
    -0.24
    ä¸īä½į
    -0.23
    ``
    -0.23
    angan
    -0.23
    fun
    -0.23
     triangular
    -0.23
    風
    -0.23
    POSITIVE LOGITS
     there
    0.35
    å·ŀå¸Ĥ
    0.30
     There
    0.28
    “There
    0.28
    ToWorld
    0.27
    é©¿ç«Ļ
    0.27
     theres
    0.26
     interchange
    0.26
    there
    0.26
    овое
    0.26
    Activations Density 0.142%

    No Known Activations