© 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. 13655
    Prev
    Next
    INDEX
    Explanations

    from words

    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
     sweeping
    -0.08
     sweeps
    -0.07
     early
    -0.06
     aggressive
    -0.06
     sweep
    -0.06
     Sweep
    -0.06
     aggressively
    -0.06
    hammer
    -0.06
    åĿĩéĩĩçĶ¨
    -0.06
     formidable
    -0.06
    POSITIVE LOGITS
     presumably
    0.09
    è¿Ļç§įä¸ľè¥¿
    0.09
    æĺ¾çĦ¶
    0.08
    çĶŁæ´»ä¼ļ
    0.08
    SEMB
    0.08
    AINER
    0.08
     feas
    0.08
    umably
    0.08
     ordinarily
    0.08
    ç»ĻåĪ«äºº
    0.08
    Activations Density 0.105%

    No Known Activations