© 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. 40972
    Prev
    Next
    INDEX
    Explanations

    current/full

    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
    heed
    -0.08
    olf
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    åİĨä»»
    -0.07
    éĶĻ
    -0.07
    åħ±
    -0.07
    squ
    -0.06
    chel
    -0.06
    åģ¶
    -0.06
    _FP
    -0.06
    POSITIVE LOGITS
    å¾ħå®ļ
    0.11
    æļĤæľª
    0.11
    å¾ħ
    0.11
    å°ļæľª
    0.10
     Belum
    0.10
     pending
    0.10
    ä¸įç¡®å®ļ
    0.09
     belum
    0.09
    pending
    0.09
    缮åīįæŃ£åľ¨
    0.09
    Activations Density 0.104%

    No Known Activations