© 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. 6639
    Prev
    Next
    INDEX
    Explanations

    3

    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
    ç¯ĩ
    -0.30
     pul
    -0.27
    iel
    -0.25
    pte
    -0.25
    _br
    -0.24
     unt
    -0.24
     br
    -0.24
     Br
    -0.24
    +Sans
    -0.23
    aval
    -0.23
    POSITIVE LOGITS
    大大å°ıå°ı
    0.26
    веÑģÑĤ
    0.25
    iff
    0.25
    åIJĦç§įåIJĦæł·
    0.24
    ãĥ¢ãĥĩ
    0.24
    æĥ¶
    0.24
    俶
    0.23
     vaguely
    0.23
     previously
    0.23
    çļĦä¿¡å¿ĥ
    0.23
    Activations Density 0.012%

    No Known Activations