© 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. 34325
    Prev
    Next
    INDEX
    Explanations

    even or odd positions

    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
    寰
    -0.08
    eor
    -0.08
    cono
    -0.08
    коÑĤа
    -0.07
    ixa
    -0.07
    ries
    -0.07
    ÙıÙĨ
    -0.07
    çľ¼ä¸Ń
    -0.07
    æ°´ä¸Ń
    -0.07
    amac
    -0.07
    POSITIVE LOGITS
    -number
    0.08
    å¥ĩ
    0.08
     odd
    0.07
    odd
    0.07
    halb
    0.07
    yssey
    0.07
     freig
    0.07
    ieg
    0.06
     numbered
    0.06
    åĩºå¥ĩ
    0.06
    Activations Density 0.012%

    No Known Activations