© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17242
    Prev
    Next
    INDEX
    Explanations

    binary tree node structure

    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
    ily
    -0.09
    anee
    -0.08
     inv
    -0.07
    acker
    -0.07
    meer
    -0.07
    è±Į
    -0.07
     eingeb
    -0.07
    oad
    -0.07
    ÙİعÙİ
    -0.07
    immy
    -0.07
    POSITIVE LOGITS
    å·¦åı³
    0.07
    æī¿
    0.07
    _handlers
    0.07
    iop
    0.07
    unit
    0.07
    æ¯Ķè¾ĥ大
    0.07
    æľ¬çº§
    0.06
     Bernstein
    0.06
    å¤ļ大
    0.06
    èĪĴ
    0.06
    Activations Density 0.009%

    No Known Activations