© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6768
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è°¶
    -0.29
    clid
    -0.28
    shots
    -0.25
    osity
    -0.25
     unfair
    -0.24
    ús
    -0.23
    å±Ĭ
    -0.23
    baÅŁÄ±
    -0.23
    OfClass
    -0.23
    åħ¶æ¬¡
    -0.23
    POSITIVE LOGITS
    éĤ£ä¸ĢåĪ»
    0.27
    åĽ
    0.26
    ç»ĻæĤ¨
    0.26
    æĬ¬èµ·
    0.25
    rimp
    0.25
    å¼ĭ
    0.25
    ANK
    0.25
    éĻĽ
    0.24
    å¹´ä¸ĬåįĬå¹´
    0.24
    éĩĩ纳
    0.24
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.