© 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. 34308
    Prev
    Next
    INDEX
    Explanations

    slug and gaps

    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
    缸è¾ħ缸æĪIJ
    -0.08
    欢è¿İåIJĦä½į
    -0.08
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.08
    ighton
    -0.08
     Bowman
    -0.08
    èļĬåŃIJ
    -0.08
    eil
    -0.08
    æĭħ
    -0.08
     Curse
    -0.08
    ilig
    -0.08
    POSITIVE LOGITS
    éľ
    0.07
    locks
    0.07
    us
    0.07
    ç»ĪçĶŁ
    0.07
    æĹłçŁ¥
    0.06
    wood
    0.06
    v
    0.06
    fest
    0.06
     diagram
    0.06
    L
    0.06
    Activations Density 0.001%

    No Known Activations