© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14589
    Prev
    Next
    INDEX
    Explanations

    in essence, the highest, to add

    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
    èĩ
    -0.08
    å°Ķ夫
    -0.08
    æ§Ľ
    -0.07
    Ñīенко
    -0.07
    åį±æ©Ł
    -0.07
    uitable
    -0.07
    æŃ»æ´»
    -0.07
    guan
    -0.07
    icl
    -0.07
    PI
    -0.07
    POSITIVE LOGITS
    à®ŀ
    0.07
    æ°Ķå¾Ĺ
    0.07
    ë§IJ
    0.06
     propos
    0.06
    婪
    0.06
    åľ¨éĩij
    0.06
     conviction
    0.06
    onii
    0.06
     convict
    0.06
    OUNTRY
    0.06
    Activations Density 0.006%

    No Known Activations