© 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. 1383
    Prev
    Next
    INDEX
    Explanations

    well, okay, guess, honest

    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
    .native
    -0.08
    yai
    -0.08
    èĥ½å¤Łæ»¡è¶³
    -0.08
    æĹ¢èĥ½
    -0.08
    شتÙĩ
    -0.08
    plementation
    -0.08
     dér
    -0.08
    ØŃÙĬÙĨ
    -0.08
    æ±Ĥ羣
    -0.08
    夫æĸ¯åŁº
    -0.08
    POSITIVE LOGITS
    ally
    0.07
    ome
    0.07
    OME
    0.06
    ...
    0.06
    odo
    0.06
     no
    0.06
    ovi
    0.06
     Pend
    0.06
    /e
    0.06
    åĿ
    0.06
    Activations Density 0.002%

    No Known Activations