© 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. 19301
    Prev
    Next
    INDEX
    Explanations

    cost

    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
    çªĥ
    -0.28
    ufs
    -0.26
    ĥģ
    -0.25
    éľīç´ł
    -0.25
    Gear
    -0.24
    kip
    -0.24
     suites
    -0.24
    éĿ¢
    -0.24
    é¦Ī
    -0.24
    splice
    -0.23
    POSITIVE LOGITS
     cost
    0.39
    æĪIJæľ¬
    0.36
    cost
    0.32
    _cost
    0.31
     Cost
    0.31
     cos
    0.29
    coat
    0.28
     costa
    0.28
    iform
    0.27
    .cost
    0.27
    Activations Density 0.011%

    No Known Activations