© 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. 45388
    Prev
    Next
    INDEX
    Explanations

    numbers and words like naturally

    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
    ìĸ´ëĤĺ
    -0.06
    æŃ£ç¡®è®¤è¯Ĩ
    -0.06
    èĩªæĪijä»ĭç»į
    -0.06
    oret
    -0.06
    oola
    -0.06
     «
    -0.06
    èĩªå·±çļĦ人çĶŁ
    -0.06
    stit
    -0.06
     "
    -0.06
    课ç¨ĭ设置
    -0.06
    POSITIVE LOGITS
    ĤŃ
    0.08
    åį¯
    0.08
    ifetime
    0.08
    ä¸įå®ĮçļĦ
    0.08
    éĵ®
    0.07
    icarbon
    0.07
    ucene
    0.07
    TML
    0.07
    yster
    0.07
    礴
    0.07
    Activations Density 0.002%

    No Known Activations