© 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. 17877
    Prev
    Next
    INDEX
    Explanations

    spectral norm of matrices

    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
    erts
    -0.09
    _lengths
    -0.07
    esar
    -0.07
    ulina
    -0.07
    ende
    -0.07
    ertz
    -0.06
    éįĬ
    -0.06
    éģĶ人
    -0.06
    åı£éķĩ
    -0.06
     ÐĹаÑĤо
    -0.06
    POSITIVE LOGITS
    éļı
    0.07
    æĹ¥æĬ¥
    0.07
    åľ¨æ¯ı个
    0.07
    éĩĩæł·
    0.07
    éļıå¤Ħ
    0.07
    å±Ģéĥ¨
    0.07
    æļĩ
    0.07
    çĤ¹è¿Ľè¡Į
    0.07
     spect
    0.07
    สรร
    0.07
    Activations Density 0.020%

    No Known Activations