© 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. 64404
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ¯ıä¸Ģä½į
    -0.27
    èѬ
    -0.27
    æŀ¶
    -0.26
     quick
    -0.25
    ights
    -0.25
    å®ĺç½ij
    -0.24
    æĬĹæĭĴ
    -0.24
    ök
    -0.24
    _nr
    -0.24
     pear
    -0.24
    POSITIVE LOGITS
    opal
    0.26
    ÅĽci
    0.24
    æĢ»äº§åĢ¼
    0.24
    ufact
    0.23
     interven
    0.23
    å¤Ħå¤Ħéķ¿
    0.23
    linky
    0.23
    èħŃ
    0.23
    ufe
    0.23
    dom
    0.22
    Activations Density 84.984%

    No Known Activations

    This feature has no known activations.