© 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. 25-TRANSCODER-HP
    7. 107415
    Prev
    Next
    INDEX
    Explanations

    Code and foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appe
    -0.34
    andy
    -0.29
    ONO
    -0.28
    çļĦæĥħ绪
    -0.27
    Editors
    -0.26
    .pose
    -0.26
    -plugins
    -0.26
    æĶ¹è£ħ
    -0.25
     Validators
    -0.25
    cdc
    -0.25
    POSITIVE LOGITS
    æĿ¥æī¾
    0.28
    avor
    0.26
    ÅĦst
    0.26
    åĢŁ
    0.25
    åĸĿèĮ¶
    0.25
    icl
    0.25
    aternity
    0.25
    è¿ĽåĨĽ
    0.24
    è¢ĭåŃIJ
    0.24
    athers
    0.24
    Activations Density 0.122%

    No Known Activations