© 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. 18154
    Prev
    Next
    INDEX
    Explanations

    Owner, protected, MONTH, action, Type, color, empty

    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
    çİ°åľ¨æĪij
    -0.07
    ovor
    -0.07
     NSMutable
    -0.07
    haw
    -0.06
    è£ķ
    -0.06
    borough
    -0.06
    thouse
    -0.06
    é¢IJåĴĮ
    -0.06
    åĭŁ
    -0.06
    åł
    -0.06
    POSITIVE LOGITS
    æĮĩå®ļçļĦ
    0.11
     specified
    0.11
    specified
    0.10
    æĮĩå®ļ
    0.09
    pecified
    0.08
    Requested
    0.08
    given
    0.08
    éĥ¨ç½²è¦ģæ±Ĥ
    0.08
     GIVEN
    0.08
     claimed
    0.07
    Activations Density 0.050%

    No Known Activations