© 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. 1254
    Prev
    Next
    INDEX
    Explanations

    is/are/being followed by descriptive state

    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
    åħ¬åı¸åıijå±ķ
    -0.08
    æ·³
    -0.06
    åĪ°ä½į
    -0.06
    åĴĮé£İéĻ©
    -0.06
    æµģè¡Į
    -0.06
     cuis
    -0.06
    æĸ°æĢĿè·¯
    -0.06
    æģ¯
    -0.06
    elus
    -0.06
    rada
    -0.05
    POSITIVE LOGITS
     neither
    0.09
    å°ıæıIJ示
    0.08
    annonce
    0.08
    羣æŃ£åľ°
    0.08
    sembl
    0.08
     Neither
    0.08
    ähler
    0.08
    èµĸ以
    0.07
    ither
    0.07
    EDO
    0.07
    Activations Density 0.087%

    No Known Activations