© 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. 15060
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and quoted words

    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
     nothing
    -0.06
    nt
    -0.06
    åĺĽ
    -0.06
    fim
    -0.06
    —in
    -0.05
    uter
    -0.05
     appendix
    -0.05
    omatis
    -0.05
    è°Ĩ
    -0.05
    cluding
    -0.05
    POSITIVE LOGITS
    为æķ°
    0.09
    ½ij
    0.08
    åĽŃè·¯
    0.08
     Ilmais
    0.08
    ithe
    0.08
    å·²ä¹ħ
    0.08
    女éĥİ
    0.08
    ennes
    0.08
    å·¥ä½ľè¿Ľè¡Į
    0.08
     essayé
    0.07
    Activations Density 0.023%

    No Known Activations