© 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. 2023
    Prev
    Next
    INDEX
    Explanations

    sphere revolving around another sphere

    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
     unwind
    -0.07
    unts
    -0.07
    éļıé£İ
    -0.07
     fetish
    -0.07
    rending
    -0.07
     redhead
    -0.07
    ç¼®
    -0.07
     Noir
    -0.06
     unfamiliar
    -0.06
     Crossing
    -0.06
    POSITIVE LOGITS
    è¦ģæ±Ĥåħ¶
    0.10
    mie
    0.09
    ä¸İ大
    0.08
    å°½åħ¶
    0.08
    entrant
    0.08
    åĪĨ享åĨħ容
    0.08
    /rfc
    0.08
    _constraint
    0.08
    è´´åIJĪ
    0.07
    éĿłçĿĢ
    0.07
    Activations Density 0.009%

    No Known Activations