© 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. 20-TRANSCODER-HP
    7. 108050
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħĭèݱ
    -0.26
     Implemented
    -0.26
    ä¹±
    -0.25
    arine
    -0.24
    -point
    -0.24
    ä¸ĢçĤ¹
    -0.24
    èĥ«
    -0.23
    ấm
    -0.23
    osite
    -0.23
    leston
    -0.23
    POSITIVE LOGITS
    幡
    0.28
    (delegate
    0.26
    ches
    0.26
    该æ¡Ī
    0.25
    affles
    0.25
    OfFile
    0.24
    igital
    0.24
     lookout
    0.24
    è¯ģåĪ¸äº¤æĺĵ
    0.24
    nas
    0.24
    Activations Density 29.654%

    No Known Activations

    This feature has no known activations.