© 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. 927
    Prev
    Next
    INDEX
    Explanations

    mathematical structure

    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
    REW
    -0.08
    ä¹ĭä½į
    -0.08
    redito
    -0.07
    aaS
    -0.07
    aeda
    -0.07
    ects
    -0.07
    ÙħØŃ
    -0.07
    _aliases
    -0.07
    REDIT
    -0.07
    ONGLONG
    -0.07
    POSITIVE LOGITS
     Watkins
    0.07
    åģ¿
    0.07
    è¶ħ
    0.07
    à¤Ĥत
    0.07
    vani
    0.07
    æĺŁæĺŁ
    0.07
    odb
    0.07
     Proof
    0.06
    åħĶ
    0.06
     h
    0.06
    Activations Density 0.006%

    No Known Activations