© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163014
    Prev
    Next
    INDEX
    Explanations

    to

    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
    egan
    -0.26
    ìĨIJ
    -0.26
    .stack
    -0.25
    ercul
    -0.25
    rag
    -0.25
     durations
    -0.24
    rang
    -0.24
    รà¸Ńà¸ĩ
    -0.24
     domestically
    -0.24
     Dip
    -0.24
    POSITIVE LOGITS
     wherever
    0.31
    è¿ľå¤Ħ
    0.28
    èĢĥæł¸
    0.27
     Vaults
    0.25
    åIJĪéĢĤ
    0.25
    $where
    0.24
    æıIJåIJį
    0.24
    满æĦı
    0.23
     preference
    0.23
    空
    0.23
    Activations Density 0.005%

    No Known Activations