© 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. 34282
    Prev
    Next
    INDEX
    Explanations

    Ps, record, Ansatz, ion, ack, content, transformed

    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
    Ñħол
    -0.08
    ä¸Ģç«Ļ
    -0.07
    æīĵå¾Ĺ
    -0.06
    æľīä¸Ģ座
    -0.06
    èģĶç½ij
    -0.06
    ongan
    -0.06
    ç»ıæŁ¥
    -0.06
    uch
    -0.06
    ä¸Ģ家人
    -0.06
    utz
    -0.06
    POSITIVE LOGITS
    ephir
    0.08
    éph
    0.08
     ims
    0.08
    å®ŀåIJįåĪ¶
    0.08
    ä½łèº«è¾¹
    0.07
    ä¸į顺
    0.07
    SURE
    0.07
    .bootstrap
    0.07
    εί
    0.07
    ä¸į离
    0.07
    Activations Density 0.007%

    No Known Activations