© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9395
    Prev
    Next
    INDEX
    Explanations

    Contrasting statements

    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
    ä¸įä¸ĭ
    -0.27
    antry
    -0.25
    elah
    -0.24
    lyph
    -0.24
    constexpr
    -0.24
     Pause
    -0.24
     consist
    -0.23
     Amar
    -0.23
    éĢļè¡Įè¯ģ
    -0.23
    à¹Ħหว
    -0.23
    POSITIVE LOGITS
    ponent
    0.28
    ttp
    0.27
    pped
    0.26
    logan
    0.26
    ires
    0.25
     attempts
    0.24
    resh
    0.24
     Breed
    0.23
    gni
    0.23
    čč↵
    0.23
    Activations Density 0.375%

    No Known Activations