© 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. 163004
    Prev
    Next
    INDEX
    Explanations

    Content distribution and legal terms

    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
     sor
    -0.29
     IH
    -0.27
     local
    -0.26
    éĢļ
    -0.25
    ,private
    -0.25
    ation
    -0.25
    å¾®åŀĭ
    -0.25
     Ion
    -0.25
     ign
    -0.24
     potential
    -0.24
    POSITIVE LOGITS
    endon
    0.32
    turned
    0.25
    TURN
    0.25
     TURN
    0.24
    uced
    0.24
    ocaust
    0.24
    endi
    0.24
    çīº
    0.23
    @endsection
    0.23
    èĽİ
    0.23
    Activations Density 0.012%

    No Known Activations