© 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. 45007
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and mathematical expressions

    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
    å®Įä¹ĭåIJİ
    -0.07
    thers
    -0.07
    ÅĤÄħ
    -0.07
     }}}
    -0.07
    ×ķ×ŀ
    -0.06
    trut
    -0.06
    ä¸įä¸Ģ
    -0.06
     pia
    -0.06
    æŃ¤èµ·
    -0.06
    üns
    -0.06
    POSITIVE LOGITS
     beraber
    0.09
    iau
    0.08
    æĪĸå°ij
    0.07
    èijĨ
    0.07
    uality
    0.07
     lagi
    0.07
    ÑģнÑĥÑİ
    0.07
    icare
    0.07
    ylene
    0.07
    पाल
    0.07
    Activations Density 0.008%

    No Known Activations