© 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. 62420
    Prev
    Next
    INDEX
    Explanations

    is and isn't

    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
    åĪ°åĮĹ京
    -0.07
    éĽ¯
    -0.07
    vedi
    -0.06
     Oaks
    -0.06
    æĤ¸
    -0.06
    羸åŃIJ
    -0.06
    ja
    -0.06
    bro
    -0.06
    æľīä¸ĢåįĬ
    -0.06
    imoto
    -0.06
    POSITIVE LOGITS
    éģ¿åħįäºĨ
    0.10
     avoided
    0.09
     âĿ
    0.09
    éĩįæĿ¥
    0.09
     certain
    0.09
    æŁIJäºĽ
    0.09
    éģ¿åħį
    0.09
    Avoid
    0.09
     avoid
    0.08
     Avoid
    0.08
    Activations Density 0.134%

    No Known Activations