© 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. 57204
    Prev
    Next
    INDEX
    Explanations

    periodic, repetitive, random, symmetric, categorical

    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
    çĥ¨
    -0.08
     неÑģÑĤандаÑĢÑĤ
    -0.08
    ä¸İçłĶ究
    -0.08
    åıĬ产åĵģ
    -0.08
    dana
    -0.08
    ÑĢоб
    -0.08
    ierra
    -0.08
    enberg
    -0.08
     meteen
    -0.08
    áĥŃ
    -0.08
    POSITIVE LOGITS
    -ish
    0.11
    åĴĮéĿŀ
    0.09
    ä¸Ķ
    0.09
    ä¸Ķåħ·æľī
    0.08
     nature
    0.08
    /non
    0.08
    åĴĮå¤ļ
    0.08
    æĢ§
    0.08
    -like
    0.07
    ä¸Ķæľī
    0.07
    Activations Density 0.074%

    No Known Activations