© 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. 23878
    Prev
    Next
    INDEX
    Explanations

    Mixed text sources

    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
    lain
    -0.32
    éĿ¢ä¸´çļĦ
    -0.30
     facing
    -0.30
     faced
    -0.28
    plain
    -0.26
     foss
    -0.26
     emissions
    -0.26
     removeFrom
    -0.25
     contest
    -0.25
     uncon
    -0.25
    POSITIVE LOGITS
    éĤ»å±ħ
    0.32
     humanity
    0.28
     Humanity
    0.28
    .summary
    0.27
    家人
    0.26
    stab
    0.26
    åħ¨åĽ½äººæ°ij
    0.26
     taxpayers
    0.26
    .Summary
    0.25
     ].
    0.25
    Activations Density 0.002%

    No Known Activations