© 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. 140955
    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
    æ´Ĺ澡
    -0.25
    å¹´ç»Ī
    -0.25
     gratuites
    -0.25
     Brent
    -0.25
    lear
    -0.24
    _Port
    -0.24
    åĨķ
    -0.24
    eyer
    -0.24
    åIJĮå¿ĥ
    -0.24
    /git
    -0.24
    POSITIVE LOGITS
    érica
    0.30
    adb
    0.26
    ç¾ģ
    0.25
    åı¯è¡ĮæĢ§
    0.25
    çªĹ
    0.25
    ela
    0.24
    çļĦæľīæķĪ
    0.24
     fragmentation
    0.24
    á»ģ
    0.24
    麹
    0.24
    Activations Density 23.855%

    No Known Activations

    This feature has no known activations.