© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30286
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with operands

    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
    icle
    -0.09
    icles
    -0.08
    ologa
    -0.08
    cente
    -0.08
    enance
    -0.08
    åľ¨äº¬
    -0.08
    表éĿ¢æ´»æĢ§
    -0.08
    taire
    -0.07
    æīijéĿ¢
    -0.07
    erja
    -0.07
    POSITIVE LOGITS
    æī¬
    0.07
    éªĦéĺ³
    0.07
    ycz
    0.06
    —the
    0.06
    èĭĩ
    0.06
    forming
    0.06
    æ£īèĬ±
    0.06
    pek
    0.06
    红æŀ£
    0.06
    utches
    0.06
    Activations Density 0.005%

    No Known Activations