© 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. 161702
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¸įè¿ľ
    -0.27
    äºĨä¸Ģéģį
    -0.26
    estic
    -0.25
    æģĻ
    -0.25
    å¼Ģæľº
    -0.24
    Discovery
    -0.24
    ÃŃst
    -0.24
    ="$(
    -0.24
    iat
    -0.24
    äºĨä¸Ģæī¹
    -0.24
    POSITIVE LOGITS
     grad
    0.26
    ç»ĻåĪ«äºº
    0.25
    大åĵ¥
    0.24
    ocos
    0.24
    nero
    0.24
    zego
    0.23
    .geometry
    0.23
    éĿ¢æĿ¿
    0.23
    oting
    0.23
     composition
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.