© 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. 38191
    Prev
    Next
    INDEX
    Explanations

    Peace and conservation

    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
     manh
    -0.09
    ossal
    -0.08
    irage
    -0.08
    ãĤ¾
    -0.08
    пÑĥÑģк
    -0.07
    yne
    -0.07
    vell
    -0.07
    compressed
    -0.07
    иÑģи
    -0.07
    æĶ¾ç©º
    -0.07
    POSITIVE LOGITS
    æĪı
    0.09
    å®ĪæģĴ
    0.08
    æ¡IJ
    0.08
    è¡¡
    0.07
    æµģ
    0.07
    移
    0.07
     Accountability
    0.07
     Cesare
    0.06
     conservation
    0.06
     Proper
    0.06
    Activations Density 0.008%

    No Known Activations