© 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. 8983
    Prev
    Next
    INDEX
    Explanations

    scientific/medical publications

    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
    å±Ĥ
    -0.32
    ä»
    -0.31
    yle
    -0.29
     third
    -0.28
    cott
    -0.26
    auge
    -0.26
    PEC
    -0.26
    oref
    -0.26
    opal
    -0.26
    éĻªåIJĮ
    -0.25
    POSITIVE LOGITS
    ç¯ģ
    0.27
    é»ijçĻ½
    0.27
    "&
    0.27
     sorte
    0.26
    alsy
    0.26
     setActive
    0.25
     Kes
    0.25
    &p
    0.24
     whit
    0.24
    å¸ĤæķĻèĤ²å±Ģ
    0.24
    Activations Density 0.043%

    No Known Activations