© 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. 44022
    Prev
    Next
    INDEX
    Explanations

    reduction of molecules

    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
    空éĻį
    -0.09
    èIJ½
    -0.08
    å¨ģ严
    -0.08
    ä¸įèIJ½
    -0.08
    é«ĺè·Łéŀĭ
    -0.07
    èŀŁ
    -0.07
    缺ä¸Ģ
    -0.07
    严åİī
    -0.07
    éĻįèIJ½
    -0.07
    æĸ¯åį¡
    -0.07
    POSITIVE LOGITS
    èĩªåıij
    0.09
     spontaneously
    0.09
     Submission
    0.08
     submitting
    0.08
     spont
    0.08
    Submitting
    0.08
     submission
    0.08
     submit
    0.08
     submits
    0.07
    omm
    0.07
    Activations Density 0.010%

    No Known Activations