© 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. 13675
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions

    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
    OK
    -0.07
    دة
    -0.06
    βο
    -0.06
    iong
    -0.06
    enticate
    -0.06
    çĿĢèĦ¸
    -0.06
    æĥļ
    -0.06
    èĻ½çĦ¶
    -0.06
    å½ĵ头
    -0.06
    apte
    -0.06
    POSITIVE LOGITS
    IJ
    0.10
    osoph
    0.08
    eature
    0.08
    ãĤĬ
    0.08
    ihe
    0.08
    soever
    0.08
     (!((
    0.08
    ieme
    0.08
    adlo
    0.08
    Msp
    0.08
    Activations Density 0.009%

    No Known Activations