© 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. 61841
    Prev
    Next
    INDEX
    Explanations

    fiscal year or dates

    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
    inster
    -0.07
    åIJĮæĹ¥
    -0.07
    iqueta
    -0.06
    äºĭåĬ¡
    -0.06
    üs
    -0.06
    pia
    -0.06
     nè
    -0.06
    ç»Ļ大家åĪĨ享
    -0.06
     MR
    -0.06
     pec
    -0.06
    POSITIVE LOGITS
    大æ¦Ĥ
    0.08
    apy
    0.08
    approx
    0.07
    artige
    0.07
    åĩºå¤´
    0.07
     approximate
    0.07
    ç²Ĺçķ¥
    0.07
     Seben
    0.07
    lje
    0.07
     gobi
    0.07
    Activations Density 0.296%

    No Known Activations