© 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. 43610
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases or code blocks

    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
    M
    -0.06
    lj
    -0.06
    ur
    -0.06
     pel
    -0.06
    ç¦Ħ
    -0.06
    é«ĺå³°
    -0.05
    带çļĦ
    -0.05
    chk
    -0.05
    å½¢å¼ı
    -0.05
    ripp
    -0.05
    POSITIVE LOGITS
    @Api
    0.09
    å¹³æ¹ĸ
    0.09
    å¿
    0.08
    ritos
    0.08
    æ¯ıå¹³æĸ¹ç±³
    0.08
    åĪļæīį
    0.08
    whose
    0.08
    óra
    0.08
    iminal
    0.08
     sema
    0.07
    Activations Density 0.001%

    No Known Activations