© 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. 3355
    Prev
    Next
    INDEX
    Explanations

    possibly, sometimes, occasionally

    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
     nämlich
    -0.07
    alha
    -0.07
     totiž
    -0.06
    ondi
    -0.06
    æijĨåľ¨
    -0.06
     Nimbus
    -0.06
    INH
    -0.06
    aga
    -0.06
    åĨĪ
    -0.06
    并éĿŀæĺ¯
    -0.06
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.10
    è¾ħ以
    0.09
    çļĦè¿ĺæľī
    0.09
     additional
    0.09
     other
    0.08
     others
    0.08
    çļĦåħ¶ä»ĸ
    0.08
    åħ¶ä»ĸ
    0.08
     optionally
    0.08
     additionally
    0.08
    Activations Density 0.087%

    No Known Activations