© 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. 3844
    Prev
    Next
    INDEX
    Explanations

    tells, says, indicates, suggests, guesses

    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
    vester
    -0.08
    nye
    -0.08
    åľ¨è¿Ļæł·çļĦ
    -0.08
    æīĢæľīè¿ĻäºĽ
    -0.08
    enburg
    -0.08
    bilder
    -0.08
     leck
    -0.08
     hiervoor
    -0.07
    è¿Ļæł·å°±åı¯ä»¥
    -0.07
    详æĥħ请
    -0.07
    POSITIVE LOGITS
     though
    0.07
    ilon
    0.07
    aint
    0.06
    though
    0.06
    è¨Ģä¹ĭ
    0.06
    æݨæµĭ
    0.06
    actions
    0.06
    ä¸Ģå¸Ĩé£İ顺
    0.06
    anged
    0.06
    ailer
    0.06
    Activations Density 0.006%

    No Known Activations