© 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. 40103
    Prev
    Next
    INDEX
    Explanations

    OR, ||, ;, .getChildAt,

    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
    .insertBefore
    -0.07
    odash
    -0.06
    ède
    -0.06
    群æĺŁ
    -0.06
    Eb
    -0.06
     distorted
    -0.06
     pró
    -0.06
    locking
    -0.06
    çĮľä½łåĸľæ¬¢
    -0.06
    ouro
    -0.06
    POSITIVE LOGITS
     individually
    0.08
    åIJĦèĩªçļĦ
    0.07
    _OVERFLOW
    0.07
    èªĵ
    0.07
    æ¡ĥåľĴ
    0.07
    ói
    0.07
    åĪĨåĪ«ä¸İ
    0.07
    è¾ħæĸĻ
    0.06
    chner
    0.06
     Foreign
    0.06
    Activations Density 0.032%

    No Known Activations