© 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. 18250
    Prev
    Next
    INDEX
    Explanations

    language decline or missing

    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
    _DI
    -0.08
    andel
    -0.08
    uhi
    -0.08
    adu
    -0.08
    iette
    -0.07
    óż
    -0.07
    פ×ķת
    -0.07
    ä¼Ł
    -0.07
    ampion
    -0.07
    मà¥įम
    -0.07
    POSITIVE LOGITS
    è¡¥æķij
    0.12
    諦
    0.10
     недоÑģÑĤа
    0.10
    åħĭæľį
    0.09
    ä¸įçĶĺå¿ĥ
    0.09
    éĩįæĸ°
    0.09
    缺失
    0.09
    æĶ¹è¿Ľ
    0.09
     missing
    0.09
    åħĭæľįåĽ°éļ¾
    0.09
    Activations Density 0.605%

    No Known Activations