© 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. 40351
    Prev
    Next
    INDEX
    Explanations

    Gnathonemus, Kosciuszko, Chespirito

    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
    oze
    -0.06
     anybody
    -0.06
    éĵ¿éĶµ
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    sz
    -0.06
    ishes
    -0.06
    они
    -0.06
    sf
    -0.06
    ä¸įè¯Ĩ
    -0.06
    zte
    -0.05
    POSITIVE LOGITS
    opedia
    0.10
    0.09
    insky
    0.09
    pedia
    0.09
    inand
    0.09
    ÙĪرد
    0.08
     **—
    0.08
    enberg
    0.08
    ertools
    0.08
    iform
    0.08
    Activations Density 0.340%

    No Known Activations