© 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. 20080
    Prev
    Next
    INDEX
    Explanations

    copyright notice or ownership

    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
    AVA
    -0.08
    äv
    -0.08
     pornos
    -0.08
    ESH
    -0.08
    ä¸ĭæĿ¥äºĨ
    -0.07
    ava
    -0.07
    ÃįN
    -0.07
    ï¼įï¼įï¼įï¼į
    -0.07
    },{
    -0.07
    ---</
    -0.07
    POSITIVE LOGITS
    ä¹ĭéŁ³
    0.07
    kest
    0.06
    theless
    0.06
    ä¹ĭéĢī
    0.06
    ç»ļ
    0.06
    .integration
    0.06
    9
    0.06
    assel
    0.05
    1
    0.05
    飩åī§
    0.05
    Activations Density 1.050%

    No Known Activations