© 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. 30-TRANSCODER-HP
    7. 95855
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å·´æĭī
    -0.30
    umph
    -0.27
     decis
    -0.26
     harvesting
    -0.26
     looping
    -0.26
     got
    -0.26
    æĸij
    -0.25
     going
    -0.25
    лÑĮ
    -0.25
     factor
    -0.25
    POSITIVE LOGITS
    TG
    0.27
     Slots
    0.25
    utions
    0.25
    æĪIJåijĺåįķä½į
    0.25
    .deserialize
    0.25
    RELEASE
    0.25
     Billion
    0.25
    ions
    0.25
    insn
    0.24
    åĽ½éĻħæľºåľº
    0.24
    Activations Density 0.893%

    No Known Activations