© 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. 19631
    Prev
    Next
    INDEX
    Explanations

    for

    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
    áĥ£áĥłáĥĺ
    -0.09
    对äºİ
    -0.08
    zelfde
    -0.07
    åħ¶çĥ¦
    -0.07
    jenigen
    -0.07
    对äºİè¿ĻäºĽ
    -0.07
    å°įæĸ¼
    -0.07
    æĪij们ä¼ļ尽快
    -0.07
    对äºİéĤ£äºĽ
    -0.07
    ãģĬéĩijãĤĴ
    -0.07
    POSITIVE LOGITS
    bidden
    0.17
    ÃŃso
    0.14
    /of
    0.13
    geries
    0.12
    /about
    0.12
    æĪijæĿ¥è¯´
    0.12
     (;;)
    0.11
    er
    0.10
    /from
    0.10
    getting
    0.10
    Activations Density 0.728%

    No Known Activations