© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33181
    Prev
    Next
    INDEX
    Explanations

    name exclamation marks

    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
    SDL
    -0.08
    apon
    -0.07
     neod
    -0.07
    æªĢ
    -0.07
    à·Ģ
    -0.07
    ric
    -0.07
    æĪijçľĭåĪ°äºĨ
    -0.06
    çł´çģŃ
    -0.06
    åĶIJ人
    -0.06
    itle
    -0.06
    POSITIVE LOGITS
     actually
    0.08
    羣æŃ£
    0.07
    åĪ°åºķæĺ¯
    0.07
     eigentlich
    0.07
    ogn
    0.07
    uilt
    0.07
    åĪ«
    0.07
    å®īä¹IJ
    0.06
    ç¾Ł
    0.06
    holm
    0.06
    Activations Density 0.077%

    No Known Activations