© 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. 18-TRANSCODER-HP
    7. 89324
    Prev
    Next
    INDEX
    Explanations

    General descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olson
    -0.32
    @include
    -0.31
    éĹ®ä»ĸ
    -0.28
    oteca
    -0.28
    ldb
    -0.28
    outines
    -0.27
    ayah
    -0.26
     przec
    -0.25
    bsite
    -0.25
     ÑĦонд
    -0.25
    POSITIVE LOGITS
    è¿«
    0.36
    æºľ
    0.31
    éŀŃ
    0.29
    鸣
    0.28
    -mount
    0.28
     Few
    0.26
     é
    0.25
     Mount
    0.25
     mount
    0.25
     tox
    0.25
    Activations Density 10.891%

    No Known Activations