© 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. 8263
    Prev
    Next
    INDEX
    Explanations

    Common English text

    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
    cert
    -0.27
    çł´
    -0.27
    D
    -0.26
     cert
    -0.26
    CLA
    -0.26
    æĬij
    -0.25
     atom
    -0.24
    æī«æıı
    -0.24
    {{--
    -0.24
    g
    -0.24
    POSITIVE LOGITS
    è¾ķ
    0.28
    abin
    0.28
    itech
    0.27
    æĩĭ
    0.27
    åŃ³
    0.26
    icator
    0.25
    ä¸Ģåľº
    0.25
    æľīä¿¡å¿ĥ
    0.25
    ÑĥменÑĤ
    0.25
     [{"
    0.25
    Activations Density 0.031%

    No Known Activations