© 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. 13197
    Prev
    Next
    INDEX
    Explanations

    end punctuation

    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
    untu
    -0.08
    缸åħ³éĹ®çŃĶ
    -0.08
    otos
    -0.08
    оÑĩÑĮ
    -0.08
    ouis
    -0.08
    _ISO
    -0.07
    kowski
    -0.07
    chaffen
    -0.07
    umbu
    -0.07
    кÑģÑĥ
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵæĿ¥è¯´
    0.08
    请éĹ®
    0.07
    éĢļ常æĥħåĨµä¸ĭ
    0.06
    __
    0.06
     typically
    0.06
    éĢļ常
    0.06
    eren
    0.06
    ably
    0.06
     According
    0.06
    è½Ł
    0.06
    Activations Density 0.024%

    No Known Activations