© 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. 163061
    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
    quan
    -0.30
    åĢŁåı£
    -0.30
    setItem
    -0.27
     Essen
    -0.27
    åĪ©çī©
    -0.26
    issant
    -0.26
    åĵ®
    -0.26
     IPP
    -0.25
    cheng
    -0.25
    æĢ§çļĦ
    -0.25
    POSITIVE LOGITS
    elder
    0.37
     increments
    0.27
    ä½Ĺ
    0.26
    eld
    0.26
    STITUTE
    0.26
     fragments
    0.25
    ounter
    0.25
    è°Ľ
    0.24
    åĪĩãĤĮ
    0.24
    fcc
    0.23
    Activations Density 0.062%

    No Known Activations

    This feature has no known activations.