© 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. 63187
    Prev
    Next
    INDEX
    Explanations

    anion/cation suffix

    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
    iya
    -0.07
    ราม
    -0.07
    elden
    -0.07
     поÑģÑĤанов
    -0.06
    è¶Ł
    -0.06
    emez
    -0.06
    owell
    -0.06
    licted
    -0.06
    çļĦæıIJé«ĺ
    -0.06
    éal
    -0.06
    POSITIVE LOGITS
     formed
    0.10
    ساÙĦ
    0.09
    åľ¨éĩĮéĿ¢
    0.08
    formed
    0.08
    å½¢æĪIJäºĨ
    0.08
    ç»ĵåIJĪåľ¨ä¸Ģèµ·
    0.08
    å½¢æĪIJçļĦ
    0.08
    衬
    0.08
    西æŀĹ
    0.08
    å½¢æĪIJ
    0.07
    Activations Density 0.008%

    No Known Activations