© 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. 57012
    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
    (MouseEvent
    -0.26
    clar
    -0.24
     Pixel
    -0.24
    ãĤ¨ãĥ«
    -0.24
    .assignment
    -0.24
    .pixel
    -0.23
    æĭ¾
    -0.23
     Imper
    -0.23
     assignment
    -0.23
    è§Ĵ
    -0.23
    POSITIVE LOGITS
    å°¼æĸ¯
    0.27
     redistrib
    0.25
     hem
    0.24
    Ĭ¶
    0.24
    educt
    0.24
    éĽªå±±
    0.24
    antu
    0.24
    çģ«å±±
    0.24
    à¤
    0.23
    è¡į
    0.23
    Activations Density 0.142%

    No Known Activations

    This feature has no known activations.