© 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. 24355
    Prev
    Next
    INDEX
    Explanations

    fail, miss, not show up

    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
    agod
    -0.08
    ç¯ł
    -0.07
    enga
    -0.07
    egos
    -0.07
    Disallow
    -0.07
    íĮ
    -0.06
     bend
    -0.06
    .nd
    -0.06
    æ±ĤçĶŁåŃĺ
    -0.06
    ìĤ´
    -0.06
    POSITIVE LOGITS
    æĹłæŃ£å½ĵçIJĨçĶ±
    0.11
    åľ¨è§Ħå®ļ
    0.10
    åľ¨è§Ħå®ļæŶéĹ´åĨħ
    0.10
    æŃ£å½ĵçIJĨçĶ±
    0.09
    åºĶæī¿æĭħ
    0.09
    éĢ¾æľŁæľª
    0.09
    æĪĸæľª
    0.09
    æĪĸ缺
    0.08
    åºĶå½ĵæī¿æĭħ
    0.08
    èĢ½è¯¯
    0.08
    Activations Density 0.095%

    No Known Activations