© 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. 20-TRANSCODER-HP
    7. 130164
    Prev
    Next
    INDEX
    Explanations

    Adverbs of manner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑĦон
    -0.26
    åīįåı°
    -0.26
    IÅŀ
    -0.25
    åĨħ容
    -0.25
    ictionaries
    -0.25
     rowspan
    -0.24
     content
    -0.24
    $I
    -0.24
    -INF
    -0.24
    _extent
    -0.24
    POSITIVE LOGITS
     resulting
    0.31
    åĽłä¸ºæĪij
    0.27
    éĿĸ
    0.27
    eneration
    0.24
    pled
    0.24
     mim
    0.24
    poon
    0.24
    _receive
    0.24
     emitting
    0.23
    ilty
    0.23
    Activations Density 7.500%

    No Known Activations