© 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. 61305
    Prev
    Next
    INDEX
    Explanations

    parenthesized mathematical variables

    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
    ness
    -0.13
    ment
    -0.07
    аÑĩ
    -0.07
    erty
    -0.07
    룬
    -0.06
    Ĩ
    -0.06
    åħ¶ä¸Ģ
    -0.06
    åħ¶ä¸ŃçļĦ
    -0.06
    ings
    -0.06
    th
    -0.06
    POSITIVE LOGITS
    éģĹçĹĩ
    0.10
    Perfil
    0.09
    ÃŃž
    0.09
    ehme
    0.09
    çĤºæŃ¢
    0.09
    à¹Į
    0.09
    uality
    0.09
    å§Ķ书记
    0.08
    åľ¨æĢĿæĥ³ä¸Ĭ
    0.08
    æĢĿæĥ³å·¥ä½ľ
    0.08
    Activations Density 0.018%

    No Known Activations