© 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. 38901
    Prev
    Next
    INDEX
    Explanations

    you may not

    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
     hopefully
    -0.10
     somit
    -0.08
     lainnya
    -0.08
     möglicherweise
    -0.08
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    -0.08
    åĬ©äºİ
    -0.08
    Ñĥк
    -0.08
    umably
    -0.08
     overshadow
    -0.08
    æĽ´åĬłå¼º
    -0.08
    POSITIVE LOGITS
     deliberately
    0.10
     tiny
    0.10
    âĢij
    0.08
     repeatedly
    0.08
     **
    0.08
     licences
    0.08
    ţi
    0.07
    tiny
    0.07
     unmistak
    0.07
     intentionally
    0.07
    Activations Density 0.004%

    No Known Activations