© 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. 45471
    Prev
    Next
    INDEX
    Explanations

    locations or extent

    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
    alian
    -0.09
    Ń
    -0.09
    nage
    -0.08
    écr
    -0.08
    rawn
    -0.07
    stown
    -0.07
    æ¯Ķäºļ
    -0.07
    uales
    -0.07
    è¶ĬãģĹ
    -0.07
    HTTPRequest
    -0.07
    POSITIVE LOGITS
    abouts
    0.13
    ä½ķå¤Ħ
    0.13
    ä»Ģä¹Īåľ°æĸ¹
    0.11
     else
    0.10
    ä¸Ģå¤Ħ
    0.10
     where
    0.10
    where
    0.09
     жиÑĤелÑĮÑģÑĤва
    0.09
    è¿ĻäºĽåľ°æĸ¹
    0.09
    θεν
    0.09
    Activations Density 0.213%

    No Known Activations