© 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. 56132
    Prev
    Next
    INDEX
    Explanations

    integral calculus

    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
    ,
    -0.06
    er
    -0.06
     (
    -0.06
    ť
    -0.05
    rib
    -0.05
     Asi
    -0.05
    ä»İåݻ年
    -0.05
    4
    -0.05
    ebab
    -0.05
    -0.05
    POSITIVE LOGITS
    hone
    0.10
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.09
    ivos
    0.09
    ัวรà¹Į
    0.09
     vá»±ng
    0.09
    é«ĺåĪĨåĪ°ä½İ
    0.09
    uksi
    0.08
    usy
    0.08
    amina
    0.08
    åıijå¸ĥä¹ĭæĹ¥èµ·
    0.08
    Activations Density 0.003%

    No Known Activations