© 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. 6786
    Prev
    Next
    INDEX
    Explanations

    forum answers/comments

    np_max-act · gemini-2.0-flash
    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
    髹
    -0.26
    iteral
    -0.26
    éĿ´
    -0.26
    -gap
    -0.26
     saddle
    -0.25
    -lfs
    -0.24
    éĥİ
    -0.24
    odyn
    -0.24
     Huffington
    -0.23
    hou
    -0.23
    POSITIVE LOGITS
    èµ·æĿ¥
    0.29
     clas
    0.27
    anted
    0.26
    eton
    0.24
    EventManager
    0.24
     against
    0.24
     center
    0.24
    ä¸ĭæĿ¥
    0.24
    bers
    0.24
     contrad
    0.24
    Activations Density 0.011%

    No Known Activations