© 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. 46300
    Prev
    Next
    INDEX
    Explanations

    per cent

    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
    riz
    -0.07
    EEE
    -0.06
    ombo
    -0.06
    CLA
    -0.06
    æĭīéĿ¢
    -0.06
    æ¡ĵ
    -0.06
    å¼Ģå§ĭæŶ
    -0.05
    joj
    -0.05
    ?'
    -0.05
    scr
    -0.05
    POSITIVE LOGITS
    Ñħай
    0.07
    idor
    0.07
    åıŃ
    0.07
    çļĦä¸Ģç¬Ķ
    0.07
    oland
    0.07
    OfString
    0.07
    onia
    0.07
    AndGet
    0.07
    enco
    0.07
    endir
    0.07
    Activations Density 0.008%

    No Known Activations