© 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. 45305
    Prev
    Next
    INDEX
    Explanations

    necessary or important

    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
     unfavor
    -0.08
    éĿŀ常ç®Ģåįķ
    -0.07
    ÙĬÙĨا
    -0.07
    igno
    -0.07
    æĹ¥æĹ¥
    -0.07
    mage
    -0.07
    åħ·æľīä¸Ģå®ļçļĦ
    -0.07
    ÙĭÙijا
    -0.07
    Allem
    -0.07
    iau
    -0.07
    POSITIVE LOGITS
     paramount
    0.07
     nötig
    0.07
    èĩ³åħ³éĩįè¦ģ
    0.07
     необÑħодимÑĭ
    0.07
     preferable
    0.07
    rites
    0.06
     Paramount
    0.06
     necessary
    0.06
    IJ
    0.06
    å¿ħè¦ģ
    0.06
    Activations Density 0.238%

    No Known Activations