© 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. 89684
    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
    __.__
    -0.30
     programm
    -0.29
    åĬłå·¥
    -0.27
     JP
    -0.25
    *pow
    -0.24
    issors
    -0.24
    odem
    -0.24
    èĬ¥
    -0.24
     proof
    -0.23
    *>(
    -0.23
    POSITIVE LOGITS
     Document
    0.25
    xac
    0.24
    oad
    0.24
    å½ĵåľ°
    0.24
    ibi
    0.24
    ph
    0.24
    ToFit
    0.24
    è·Łä¸įä¸Ĭ
    0.24
    wit
    0.24
    ä¸įç»ı
    0.24
    Activations Density 15.750%

    No Known Activations

    This feature has no known activations.