© 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. 42889
    Prev
    Next
    INDEX
    Explanations

    glassless

    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
    /tcp
    -0.07
    isz
    -0.07
    èĻ
    -0.07
    andt
    -0.07
    ntag
    -0.07
    /Runtime
    -0.07
    achu
    -0.06
    åħģ
    -0.06
    _ENCODE
    -0.06
    cope
    -0.06
    POSITIVE LOGITS
    èĻ½çĦ¶æ²¡æľī
    0.12
    èĻ½çĦ¶ä¸įæĺ¯
    0.10
    less
    0.10
     indirectly
    0.10
    çļĦåĶ¯ä¸Ģ
    0.10
    éĹ´æİ¥
    0.10
     solely
    0.09
    lessness
    0.09
     indirect
    0.09
    åĶ¯ä¸Ģ
    0.09
    Activations Density 0.419%

    No Known Activations