© 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. 89363
    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
     enclosure
    -0.27
     hall
    -0.27
    _DYNAMIC
    -0.24
    .Handled
    -0.24
    桧
    -0.24
    èĹ©
    -0.24
     Belmont
    -0.23
    åIJĮç±»
    -0.23
    æĭ±
    -0.23
    ัส
    -0.23
    POSITIVE LOGITS
    Specifier
    0.25
    inho
    0.25
    zn
    0.25
     inferred
    0.24
    Ł¥
    0.24
     Slide
    0.24
    owitz
    0.23
     cuz
    0.23
    ä¸Ĭåİ»
    0.23
    SPEC
    0.22
    Activations Density 2.203%

    No Known Activations

    This feature has no known activations.