© 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. 19-TRANSCODER-HP
    7. 8565
    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
     unaffected
    -0.27
    olson
    -0.26
    çŀ
    -0.26
    iola
    -0.26
    å½ĵåľ°çļĦ
    -0.26
    ä¸įåı¯
    -0.24
     lipstick
    -0.24
    æĺ¯åIJ¦æľī
    -0.24
    udos
    -0.24
     thinly
    -0.24
    POSITIVE LOGITS
    bm
    0.29
    åijĬ
    0.28
     democracy
    0.28
    åłĨ
    0.27
    CREASE
    0.27
     turning
    0.27
    ument
    0.27
     memory
    0.26
    çĻ¾
    0.26
    Decre
    0.25
    Activations Density 0.427%

    No Known Activations

    This feature has no known activations.