© 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. 39787
    Prev
    Next
    INDEX
    Explanations

    correspondence or via

    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
    çĿ
    -0.07
    ä»ĭ
    -0.07
    æĮ½
    -0.07
    bow
    -0.06
    åıĪæĥ³
    -0.06
     bow
    -0.06
    ews
    -0.06
    æ£
    -0.06
    æª
    -0.06
    次
    -0.06
    POSITIVE LOGITS
    Via
    0.08
     corresp
    0.08
     corresponds
    0.08
     corresponde
    0.08
    via
    0.08
    _via
    0.08
     Via
    0.08
    ä¹ŁæŃ£æĺ¯
    0.08
     correspondence
    0.08
     corres
    0.08
    Activations Density 0.046%

    No Known Activations