© 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. 50283
    Prev
    Next
    INDEX
    Explanations

    costs and prices

    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
    øre
    -0.08
    èĥ½å¤Łå¸®åĬ©
    -0.08
    á»ĵng
    -0.07
    AINED
    -0.07
    循
    -0.07
    оÑĤо
    -0.07
    åĪ°è´§
    -0.07
    ziu
    -0.07
    ymar
    -0.07
     Circular
    -0.07
    POSITIVE LOGITS
    ä¸į计
    0.08
    IPC
    0.08
    curring
    0.08
    æĿ¥è®¡ç®Ĺ
    0.07
    whose
    0.07
     calculate
    0.07
     whose
    0.07
     ØŃساب
    0.07
    adam
    0.07
     compute
    0.06
    Activations Density 0.190%

    No Known Activations