© 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. 56676
    Prev
    Next
    INDEX
    Explanations

    rational double point, III degrees, Crossdresser

    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
     salary
    -0.07
     nomin
    -0.07
     piled
    -0.06
     Crush
    -0.06
    楼å®ĩ
    -0.06
    èªł
    -0.06
     bedside
    -0.06
    HR
    -0.06
     poured
    -0.06
    æŃ£å¤§
    -0.06
    POSITIVE LOGITS
    èģĶ绾
    0.09
    _DP
    0.08
     Wenger
    0.08
    éŀ
    0.08
    弦
    0.08
    ABEL
    0.08
    yscale
    0.08
    èĤĽéŨ
    0.08
    繫
    0.08
    /oauth
    0.08
    Activations Density 0.006%

    No Known Activations