© 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. 40369
    Prev
    Next
    INDEX
    Explanations

    numbers and tables

    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
    _walk
    -0.06
    azor
    -0.06
    beck
    -0.06
     indirectly
    -0.06
     overlapping
    -0.05
    esc
    -0.05
     [...
    -0.05
     looping
    -0.05
     overlap
    -0.05
     Rough
    -0.05
    POSITIVE LOGITS
    æł¹æį®å®ŀéĻħæĥħåĨµ
    0.09
    æł¹æį®éľĢè¦ģ
    0.08
    slashes
    0.08
    åįķéĹ´
    0.08
    çļĻ
    0.08
    utura
    0.08
    åºĶæľīçļĦ
    0.08
    å°½åı¯èĥ½
    0.08
    转载请注æĺİåĩºå¤Ħ
    0.08
     sesuai
    0.07
    Activations Density 0.012%

    No Known Activations