© 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. 28930
    Prev
    Next
    INDEX
    Explanations

    suffix 'ad', 'ag', 'az', 'ink', 'aton', 'rops', 'chrom', 'ref', 'vet', 'abin'

    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
    åĽłä¸ºåıªæľī
    -0.07
    å¥Īä½ķ
    -0.07
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.07
    以赴
    -0.07
     whichever
    -0.07
    æĺ¯ä¸įåı¯èĥ½
    -0.07
    çķħæīĢ欲è¨Ģ
    -0.07
    otas
    -0.06
     INCLUDING
    -0.06
     chose
    -0.06
    POSITIVE LOGITS
    è¿Ļæĺ¯ä¸Ģç§į
    0.08
    —a
    0.08
    åİħéķ¿
    0.07
    çŃīæĸ°
    0.07
    çŃīçī¹æ®Ĭ
    0.07
    blast
    0.07
    ÑĨе
    0.07
    eve
    0.07
    æľīéģĵ
    0.07
    ãģªãģ©ãĤĤ
    0.06
    Activations Density 0.053%

    No Known Activations