© 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. 8296
    Prev
    Next
    INDEX
    Explanations

    computer programs and data

    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
    pod
    -0.27
    è¿ĩçļĦ
    -0.26
     Saud
    -0.26
    etu
    -0.26
    æľĢè¿ij
    -0.26
     pod
    -0.26
    undra
    -0.25
    ipl
    -0.25
     notamment
    -0.24
    岸
    -0.24
    POSITIVE LOGITS
    airy
    0.26
     TAKE
    0.24
    åįĸ家
    0.24
     casc
    0.24
     Baker
    0.24
    useppe
    0.23
    累积
    0.23
     Bros
    0.23
    ή
    0.23
     маÑĢÑĪ
    0.23
    Activations Density 0.054%

    No Known Activations