© 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. 6853
    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
    ä¹Łæ²¡æľī
    -0.26
    backward
    -0.26
     Alberto
    -0.26
    edly
    -0.24
    блок
    -0.24
    åľĥ
    -0.24
    edBy
    -0.23
    loff
    -0.23
    æĹ¶è¡¨ç¤º
    -0.23
    unei
    -0.23
    POSITIVE LOGITS
    æĮģæľī
    0.27
    aines
    0.26
    çĶŁäº§çļĦ
    0.26
    åŁºæľ¬åİŁåĪĻ
    0.26
    å¹´è½»çļĦ
    0.26
    aminer
    0.25
    æī§è¡Į
    0.25
    Sharper
    0.25
    èĴ½
    0.23
    èĪĴéĢĤçļĦ
    0.23
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.