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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89547
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭ¨
    -0.26
    ils
    -0.26
    ä¾Ŀæ³ķ追究
    -0.25
    cord
    -0.25
    berger
    -0.25
    attro
    -0.24
    确认
    -0.24
    è¦ģåıĬæŶ
    -0.24
    ulance
    -0.24
    quire
    -0.24
    POSITIVE LOGITS
    éĽĨæĪIJ
    0.26
    lite
    0.26
     Persistence
    0.25
     persistence
    0.25
    å®Įæķ´çļĦ
    0.24
     comparative
    0.24
    èį¡
    0.24
    å®Įæķ´
    0.23
    ç¥Ģ
    0.23
    yna
    0.23
    Activations Density 46.278%

    No Known Activations

    This feature has no known activations.