© 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. 60618
    Prev
    Next
    INDEX
    Explanations

    1:n relationship

    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
    æĹłè®ºæĺ¯åľ¨
    -0.08
    igneur
    -0.07
    flt
    -0.07
    æĹłè®ºåľ¨
    -0.07
    æĹłè®º
    -0.07
    ä¸Ģåıį
    -0.07
    strcasecmp
    -0.07
    æĹłè®ºæĺ¯
    -0.07
    _forward
    -0.07
    olt
    -0.07
    POSITIVE LOGITS
    кана
    0.07
    åħ·ä½ĵæŶéĹ´
    0.07
    anny
    0.07
    кан
    0.07
    èĢĮä¸Ķæľī
    0.07
    éľĢè¦ģçĶ¨
    0.06
    ssf
    0.06
    ä¸įèĩªè§ī
    0.06
    ä¸įåĥı
    0.06
    ÃŃb
    0.06
    Activations Density 0.016%

    No Known Activations