© 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. 17311
    Prev
    Next
    INDEX
    Explanations

    logarithm, integral, math, Vampire, invention

    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
    ä»Ĺ
    -0.08
    edur
    -0.08
    ture
    -0.08
    \models
    -0.08
    ewa
    -0.08
    æĪij社
    -0.08
    æİĸ
    -0.08
    CHAN
    -0.07
    é¾
    -0.07
    æ¯Ķä¾ĭ为
    -0.07
    POSITIVE LOGITS
    éĹ´æŃĩ
    0.07
    ichte
    0.07
    aph
    0.07
    Margin
    0.06
     margin
    0.06
    èĩªåľ¨
    0.06
    ç¿Ł
    0.06
    aper
    0.06
     Margin
    0.06
    margin
    0.06
    Activations Density 0.005%

    No Known Activations