© 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. 35-TRANSCODER-HP
    7. 40372
    Prev
    Next
    INDEX
    Explanations

    "pe" words in science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¾ĥ为
    -0.27
    åħ¨æĸ¹ä½į
    -0.26
     advertisements
    -0.26
    ä¾ĭåŃIJ
    -0.25
    ä¹ĭæĺŁ
    -0.25
     boyfriend
    -0.24
    åĪĽä¸ļèĢħ
    -0.23
    榨
    -0.23
    ìĹħì²´
    -0.23
     Saved
    -0.23
    POSITIVE LOGITS
    itat
    0.38
    iom
    0.35
    imi
    0.32
    iten
    0.31
    ival
    0.31
    ipt
    0.30
    icity
    0.30
    imin
    0.30
    iting
    0.29
    ieve
    0.29
    Activations Density 1.610%

    No Known Activations