© 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. 23-TRANSCODER-HP
    7. 24298
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fastest
    -0.27
    owell
    -0.25
    ħĮ
    -0.24
    å®
    -0.24
     starring
    -0.24
    楣
    -0.24
    ignet
    -0.23
    åIJĦæľī
    -0.23
     largest
    -0.23
    æľĢ大çļĦ
    -0.23
    POSITIVE LOGITS
    lags
    0.30
    ripp
    0.29
    ears
    0.26
    åģıåIJij
    0.25
    天河
    0.25
    pattern
    0.25
    ëĦĪ
    0.25
    èĢ³
    0.24
    perial
    0.24
    reon
    0.24
    Activations Density 0.002%

    No Known Activations