© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21393
    Prev
    Next
    INDEX
    Explanations

    sanding, polishing, grinding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chetti
    -0.08
    stag
    -0.08
     chẽ
    -0.08
    wide
    -0.08
    ç¥ŀè¯Ĩ
    -0.08
    _argv
    -0.08
    bolt
    -0.07
    gie
    -0.07
     chÆ°ng
    -0.07
    flo
    -0.07
    POSITIVE LOGITS
    磨
    0.14
    æīĵ磨
    0.13
    æĬĽåħī
    0.11
    çłĶ磨
    0.11
     polishing
    0.11
    ç²Ĺç³Ļ
    0.11
     abrasive
    0.11
    æij©æĵ¦
    0.10
     abras
    0.10
    磨æįŁ
    0.10
    Activations Density 0.043%

    No Known Activations