© 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. 8158
    Prev
    Next
    INDEX
    Explanations

    medical research/diagnostics

    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
    åĩĨç¡®
    -0.48
     correctly
    -0.46
     incorrect
    -0.44
     inaccur
    -0.44
    correct
    -0.43
     incorrectly
    -0.42
    æŃ£ç¡®
    -0.42
    accur
    -0.42
     accurately
    -0.42
     correct
    -0.41
    POSITIVE LOGITS
    åģľä¸ĭ
    0.29
    æĪij们认为
    0.29
    CriticalSection
    0.27
    åģľçĶµ
    0.26
    plr
    0.26
    åĽºå®ļçļĦ
    0.25
    hani
    0.25
    onet
    0.25
    çĽij
    0.25
    uries
    0.25
    Activations Density 0.034%

    No Known Activations