© 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. 162894
    Prev
    Next
    INDEX
    Explanations

    central

    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
     ëĭ¤ë§Į
    -0.28
    uchs
    -0.28
    æ»ļçIJĥ
    -0.28
    PIP
    -0.27
    /gif
    -0.25
    cÃŃ
    -0.25
    initWith
    -0.25
     Million
    -0.24
     Millions
    -0.24
     Bom
    -0.24
    POSITIVE LOGITS
    æį·
    0.28
    è´´
    0.28
    OC
    0.27
     opportunity
    0.27
     bi
    0.26
    á»°
    0.25
    åĨ³å®ļ
    0.25
     sec
    0.25
    åħ±æĮ¯
    0.25
    CursorPosition
    0.25
    Activations Density 0.006%

    No Known Activations