© 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. 163017
    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
    enci
    -0.31
    åĮĸè¿Ľç¨ĭ
    -0.28
    豪
    -0.27
     Malone
    -0.26
    goal
    -0.26
    Google
    -0.25
     goal
    -0.24
    æĮĤåľ¨
    -0.24
    æĤ²åĵĢ
    -0.24
    æīĵå·¥
    -0.24
    POSITIVE LOGITS
     Friday
    0.27
     physically
    0.26
    awe
    0.26
    preferred
    0.25
    ass
    0.25
    賦
    0.25
     Fridays
    0.25
    indered
    0.25
    _#{
    0.25
    _PHYS
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.