© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7237
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
    é¹ŀ
    -0.29
    qed
    -0.28
    .atomic
    -0.27
    ayas
    -0.26
     lesser
    -0.25
     Skinner
    -0.25
    åĽ½å®¶æĪĺçķ¥
    -0.25
    imei
    -0.24
     Directory
    -0.24
    angep
    -0.24
    POSITIVE LOGITS
     Trout
    0.28
     chests
    0.27
     quán
    0.26
    >(()
    0.26
    otify
    0.25
    occasion
    0.25
    è´¯
    0.25
    çļĦåij½è¿IJ
    0.25
    ourd
    0.24
     reach
    0.24
    Activations Density 0.803%

    No Known Activations