© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6259
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    æĩ¿
    -0.28
    çĶ¨æĪ·æıIJä¾Ľ
    -0.28
     []).
    -0.27
    inherits
    -0.26
    ()."
    -0.24
     èĩªåĬ¨çĶŁæĪIJ
    -0.24
    .dds
    -0.24
    ownt
    -0.24
    uppen
    -0.23
    ëĭ¨ì²´
    -0.23
    POSITIVE LOGITS
    æĸ°é²ľ
    0.28
     miscellaneous
    0.26
     despite
    0.25
     unpublished
    0.24
     remaining
    0.24
    好æ¶Īæģ¯
    0.24
    двиг
    0.24
     P
    0.24
    éŀ£
    0.24
    管å±Ģ
    0.24
    Activations Density 0.028%

    No Known Activations