© 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. 26348
    Prev
    Next
    INDEX
    Explanations

    ascertain Floating Point

    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
     tenaga
    -0.06
     related
    -0.06
     Pop
    -0.06
     Obtain
    -0.06
     pauta
    -0.06
    atty
    -0.06
    _ATOMIC
    -0.06
    ãĥ³ãĥĹ
    -0.06
    ä¼¼ä¹İåľ¨
    -0.06
    æ¬łç¼´
    -0.06
    POSITIVE LOGITS
    æĪij们å¸ĮæľĽ
    0.09
    åĪ°æŶ
    0.08
    å¿ħé¡»è¦ģæľī
    0.08
    å±ĬæŶ
    0.08
     unintended
    0.08
     nanti
    0.08
    onen
    0.08
    åĪ°æŶåĢĻ
    0.08
    alon
    0.08
    inn
    0.08
    Activations Density 0.129%

    No Known Activations