© 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. 30-TRANSCODER-HP
    7. 96647
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reactions
    -0.30
     reacts
    -0.29
    åıįåºĶ
    -0.28
     reacting
    -0.27
    åĮĸåѦ
    -0.26
     reactive
    -0.26
     chemical
    -0.26
    assium
    -0.26
    sdale
    -0.26
    chemical
    -0.25
    POSITIVE LOGITS
    uf
    0.31
    峪
    0.29
    ukan
    0.28
    oment
    0.28
    loadModel
    0.27
    Republic
    0.26
    unami
    0.26
    สาà¸ĺารà¸ĵ
    0.26
    Powered
    0.26
    注æĺİæĿ¥æºIJ
    0.25
    Activations Density 0.891%

    No Known Activations