© 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. 8682
    Prev
    Next
    INDEX
    Explanations

    code/licensing

    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
    è¿ĩåİ»äºĨ
    -0.26
     ÑĤоÑĢ
    -0.26
    /Gate
    -0.26
    åľª
    -0.26
     Dr
    -0.25
    èĥģ
    -0.25
     Wa
    -0.25
    è¦ģåģļ好
    -0.25
     orth
    -0.24
     ngo
    -0.24
    POSITIVE LOGITS
    (cps
    0.26
    解æķ£
    0.25
    efa
    0.24
    .FileInputStream
    0.24
    PerPixel
    0.24
    lek
    0.24
    åıį
    0.23
     kisses
    0.23
    nonnull
    0.23
    'y
    0.23
    Activations Density 0.013%

    No Known Activations