© 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. 24-TRANSCODER-HP
    7. 149665
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     irony
    -0.26
    pers
    -0.26
    dsl
    -0.25
    ctxt
    -0.25
    ooth
    -0.25
     Orchestra
    -0.24
    orsk
    -0.24
    æĸ¯åŁº
    -0.24
    ooky
    -0.24
    çī¹æĸ¯
    -0.23
    POSITIVE LOGITS
    ÙĦاØŃ
    0.27
    vas
    0.24
    Invocation
    0.24
    roe
    0.24
    itorio
    0.24
    ä¸Ĭåįĩ
    0.23
    éĻ²
    0.23
    å¾ĹåĪ°
    0.23
    /con
    0.23
    .getResponse
    0.23
    Activations Density 1.310%

    No Known Activations

    This feature has no known activations.