© 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. 31-TRANSCODER-HP
    7. 18553
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hom
    -0.33
    å¿Ļ
    -0.29
    æļĸ
    -0.28
    azy
    -0.28
     arom
    -0.27
    har
    -0.26
     lum
    -0.26
     Special
    -0.25
    BO
    -0.25
     debugger
    -0.25
    POSITIVE LOGITS
    è¿ĺæĺ¯è¦ģ
    0.28
    æģĭæĥħ
    0.26
    _disk
    0.25
    éĥĿ
    0.25
    液
    0.25
    issance
    0.25
    壳
    0.24
    elian
    0.24
    è°
    0.24
    icap
    0.24
    Activations Density 0.006%

    No Known Activations