© 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. 63201
    Prev
    Next
    INDEX
    Explanations

    numbers 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
    åħ¶æīĢ
    -0.07
    scribe
    -0.07
    ä¸ĢæĹģ
    -0.07
    anski
    -0.07
    epam
    -0.07
    erman
    -0.07
    olls
    -0.06
    æľĢ好
    -0.06
    velt
    -0.06
    iplinary
    -0.06
    POSITIVE LOGITS
    oris
    0.09
    ATORS
    0.07
    以身
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    tis
    0.07
    åIJİæĦŁ
    0.07
    çĪ±ç¾İ
    0.07
    zzo
    0.06
    è¨
    0.06
     opos
    0.06
    Activations Density 0.003%

    No Known Activations