© 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. 64294
    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
    éĥ½æľīçĿĢ
    -0.33
    ĥ½
    -0.28
    éĥ½æľī
    -0.27
    np
    -0.26
    å¾Īéĩįè¦ģçļĦ
    -0.26
    åıijå±ķ
    -0.25
    éĥ½æĺ¯
    -0.24
    éĩįè¦ģçļĦ
    -0.24
    &#
    -0.24
    $filter
    -0.24
    POSITIVE LOGITS
    棵æłij
    0.29
    桶
    0.29
    IMIT
    0.27
     Oaks
    0.26
    xba
    0.25
    åªĴä½ĵ
    0.25
    -media
    0.25
    erca
    0.25
     Media
    0.25
    ç¾ģ
    0.24
    Activations Density 0.148%

    No Known Activations

    This feature has no known activations.