© 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. 27-TRANSCODER-HP
    7. 8783
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®ĮæĪIJåIJİ
    -0.27
    è®¤çľŁåŃ¦ä¹ł
    -0.27
    åŃ¦ä¹ł
    -0.26
    adro
    -0.26
    ady
    -0.26
    ish
    -0.26
    onnement
    -0.25
    ishly
    -0.25
     learns
    -0.25
    صÙĦاØŃ
    -0.24
    POSITIVE LOGITS
    (*(
    0.28
     Spiral
    0.27
     spiral
    0.27
    uil
    0.26
     (*(
    0.26
    æĸĩæĺİ
    0.26
    apphire
    0.26
     prostitution
    0.25
    (compare
    0.25
    ä¾ĽçĥŃ
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.