© 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. 129939
    Prev
    Next
    INDEX
    Explanations

    Science and technology

    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
     IW
    -0.26
    _TAGS
    -0.26
    apes
    -0.25
    laps
    -0.25
     Across
    -0.25
    ipes
    -0.25
     trans
    -0.25
    _bold
    -0.24
     Walters
    -0.24
     dow
    -0.24
    POSITIVE LOGITS
    -less
    0.43
    lessness
    0.36
    -none
    0.35
    ä¸įéĢļ
    0.35
    less
    0.35
    -proof
    0.34
    nothing
    0.34
    -free
    0.34
    å°ij
    0.33
    è¾ĥå°ij
    0.33
    Activations Density 81.916%

    No Known Activations