© 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. 58023
    Prev
    Next
    INDEX
    Explanations

    road numbers

    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
     callee
    -0.07
    åģı
    -0.06
    ven
    -0.06
     أرج
    -0.06
    otp
    -0.06
    被éĢ¼
    -0.06
    ef
    -0.05
     \/
    -0.05
    etr
    -0.05
    oth
    -0.05
    POSITIVE LOGITS
    ÂŃi
    0.09
    éĿĴè¡£
    0.08
    ignet
    0.08
    CriticalSection
    0.08
    ÑĢей
    0.08
    impat
    0.08
    arth
    0.08
     Einschrän
    0.08
     пак
    0.08
    ิà¸Ļ
    0.07
    Activations Density 0.060%

    No Known Activations