© 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. 1714
    Prev
    Next
    INDEX
    Explanations

    each element or item

    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
    hausen
    -0.09
    ezz
    -0.09
    ç»ıæµİ社ä¼ļåıijå±ķ
    -0.08
    ierzch
    -0.07
    empat
    -0.07
    ellow
    -0.07
    spr
    -0.07
    åħ¶ä¸ī
    -0.07
    ixa
    -0.07
    ä¾ĿçĦ¶åľ¨
    -0.07
    POSITIVE LOGITS
    æ¡
    0.07
    ÑģÑĢе
    0.06
    çĶŁåij½
    0.06
     loop
    0.06
     promises
    0.06
    IFE
    0.06
    çģ¯
    0.06
    ç®ķ
    0.06
    æĴ
    0.05
     Loop
    0.05
    Activations Density 0.001%

    No Known Activations