© 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. 62211
    Prev
    Next
    INDEX
    Explanations

    knowledge, final, ground state

    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
    odyn
    -0.07
    iggio
    -0.06
    åĩıå°ij对
    -0.06
    gettext
    -0.06
    æĺ¯æĢİæł·
    -0.06
    ouw
    -0.06
    ajakan
    -0.06
    _SIMPLE
    -0.06
    ä¸Ĭè·¯
    -0.06
    modifier
    -0.06
    POSITIVE LOGITS
    ине
    0.08
     اÙĦÙĨÙĩائÙĬ
    0.08
    oir
    0.08
    -final
    0.07
     finali
    0.07
     final
    0.07
     اÙĦÙĨÙĩائÙĬØ©
    0.07
    _finalize
    0.07
    final
    0.07
    æľĢç»ĪçļĦ
    0.07
    Activations Density 0.009%

    No Known Activations