© 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. 38193
    Prev
    Next
    INDEX
    Explanations

    interpretations and status

    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
    spor
    -0.08
    رخ
    -0.08
    fdc
    -0.08
    ')['
    -0.08
    æĬ¥äºĨ
    -0.08
    omid
    -0.07
    åı¯å¾ª
    -0.07
    Inflater
    -0.07
    è°£
    -0.07
    è´¢è¿IJ
    -0.07
    POSITIVE LOGITS
     reinterpret
    0.09
     interpretations
    0.09
     interpret
    0.08
    åĶ¯çī©ä¸»ä¹ī
    0.08
     interpretation
    0.08
    interpret
    0.08
     Interpret
    0.08
    è§Ĥ
    0.07
    odox
    0.07
    åĶ¯çī©
    0.07
    Activations Density 0.034%

    No Known Activations