© 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. 9071
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas or inequalities

    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
    çĸı
    -0.08
    代çIJĨæľºæŀĦ
    -0.07
    代çIJĨ
    -0.07
    agar
    -0.06
    çīĪæĿĥéĹ®é¢ĺ
    -0.06
    çĤ¹å¤ļ
    -0.06
     omfatt
    -0.06
    çŃ¾åIJĪåIJĮ
    -0.06
    صرÙĬØ©
    -0.06
     Galli
    -0.06
    POSITIVE LOGITS
     ratios
    0.08
    å°±è§ģ
    0.07
     ratio
    0.07
    顺é£İ
    0.07
     Ratio
    0.07
    ä¸į失
    0.07
    樽
    0.07
    ä¸įç»ıæĦıéĹ´
    0.07
    bor
    0.07
     Overs
    0.07
    Activations Density 0.003%

    No Known Activations