© 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. 60985
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    +_
    -0.07
    <_
    -0.06
    ,
    -0.06
    abouts
    -0.06
    è¶ħé«ĺçļĦ
    -0.06
    hausen
    -0.06
    ĵ
    -0.06
    å®ĥ以
    -0.06
    tern
    -0.06
    eker
    -0.06
    POSITIVE LOGITS
    اÙģÙĬ
    0.09
    å¦ŀ
    0.07
    æĬķ稿éĤ®ç®±
    0.07
    unga
    0.07
    áĥĵáĥĶ
    0.07
    arki
    0.07
    á»ĵi
    0.07
    Äħcz
    0.07
    olg
    0.07
    obo
    0.07
    Activations Density 0.001%

    No Known Activations