© 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. 2043
    Prev
    Next
    INDEX
    Explanations

    same X, same Y

    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
    Äĵm
    -0.10
    erii
    -0.10
    ä¸Ģæĸij
    -0.10
    ׳ק
    -0.09
    aldo
    -0.09
    apkan
    -0.09
    deaux
    -0.09
    èļ£
    -0.09
    cind
    -0.09
    ayat
    -0.09
    POSITIVE LOGITS
    -sex
    0.09
    -sama
    0.08
     thing
    0.08
     Äijắn
    0.07
    iating
    0.07
    iates
    0.07
    -looking
    0.07
    ledes
    0.07
    born
    0.07
    ething
    0.06
    Activations Density 0.047%

    No Known Activations