© 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. 19651
    Prev
    Next
    INDEX
    Explanations

    git push upstream

    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
    è§Ĵ
    -0.06
    bane
    -0.06
    arius
    -0.06
     Nit
    -0.06
     str
    -0.06
    pk
    -0.06
    è§ĴçļĦ
    -0.06
    orde
    -0.05
    aria
    -0.05
    hel
    -0.05
    POSITIVE LOGITS
    elper
    0.09
    issé
    0.09
    esehen
    0.09
    /upload
    0.08
    æļĩ
    0.08
    ãĥ¼ãĤ¸ãĥ¼
    0.08
    ÎŃα
    0.08
    é«ĺå¯Ĩ
    0.08
    ÅĤÄħ
    0.08
    ichten
    0.08
    Activations Density 0.001%

    No Known Activations