© 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. 43142
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming keywords

    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
    åºĶå½ĵåľ¨
    -0.07
    踵
    -0.06
    ³
    -0.06
    æĸ¯å¡Ķ
    -0.06
    åľ¨éĺħ读
    -0.06
    åĪĻçĶ±
    -0.06
    å½ĵåħ¶
    -0.06
     Verk
    -0.06
    å¦Ĥåħ¶
    -0.06
    æĽ´åĸľæ¬¢
    -0.06
    POSITIVE LOGITS
    strup
    0.09
     "[%
    0.07
    ghi
    0.07
     tadi
    0.07
    öd
    0.07
    -inspired
    0.07
    ropping
    0.07
    ׳×ķת
    0.07
    éģIJ
    0.07
    çĻ»å½ķæŁ¥çľĭ
    0.07
    Activations Density 0.004%

    No Known Activations