© 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. 16512
    Prev
    Next
    INDEX
    Explanations

    numbers and version strings

    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
    ony
    -0.07
    硬
    -0.07
     interact
    -0.06
     hard
    -0.06
    -drive
    -0.06
    ç®Ģåįķ
    -0.06
    æĥħåĨµåıĬ
    -0.06
     {}:
    -0.06
    çĨ
    -0.06
    æī«
    -0.06
    POSITIVE LOGITS
    olare
    0.07
    å¨
    0.07
    _OPTS
    0.06
    åķ¡
    0.06
    cian
    0.06
    upal
    0.06
    onga
    0.06
    arine
    0.06
    illon
    0.06
     satisf
    0.06
    Activations Density 0.007%

    No Known Activations