© 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. 108070
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    lis
    -0.29
    TS
    -0.27
    prit
    -0.27
    pivot
    -0.27
    仪
    -0.26
    xyz
    -0.26
    hc
    -0.26
     admir
    -0.25
    n
    -0.25
    >>>
    -0.25
    POSITIVE LOGITS
    esco
    0.31
    IVO
    0.28
    çĶŁæķĪ
    0.27
    åĢĴå¡Į
    0.27
    Outputs
    0.26
    ìĤŃ
    0.25
    [vi
    0.25
    -haired
    0.25
    ichen
    0.25
    _BB
    0.25
    Activations Density 15.137%

    No Known Activations