© 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. 30732
    Prev
    Next
    INDEX
    Explanations

    constant / invariant / preserved

    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
    Ùĩاب
    -0.09
    erez
    -0.08
    à§įথ
    -0.08
    ear
    -0.08
    ambo
    -0.07
    eph
    -0.07
    ophil
    -0.07
    ä»Ĭ天å°ıç¼ĸ
    -0.07
    çĮ®ç¤¼
    -0.07
    æ¹¾åĮº
    -0.07
    POSITIVE LOGITS
     throughout
    0.08
     during
    0.07
    座ä¸Ĭ
    0.07
    /change
    0.07
     unless
    0.07
    çķħ
    0.07
    éĻ¤éĿŀ
    0.07
    å®ļå¾ĭ
    0.07
    éĻ¤äºĨåľ¨
    0.06
    acons
    0.06
    Activations Density 0.005%

    No Known Activations