© 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. 62642
    Prev
    Next
    INDEX
    Explanations

    must be

    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
    ứ
    -0.07
    ä¸Ĭæ·»
    -0.06
    çĶ¨æĦı
    -0.06
    POSIT
    -0.06
     ì§ĵ
    -0.06
    -counter
    -0.06
    æĸĽ
    -0.06
    fits
    -0.06
    åĪ°ä½į
    -0.06
    dest
    -0.06
    POSITIVE LOGITS
    æīįç®Ĺ
    0.20
    æīįèĥ½æľī
    0.20
    æīįèĥ½
    0.18
    æīįæľī
    0.17
    æīįèĥ½èİ·å¾Ĺ
    0.17
    æīįåı¯ä»¥
    0.17
    æīįèĥ½çľŁæŃ£
    0.17
    æīįåı¯
    0.16
    æīį好
    0.16
    æĸ¹èĥ½
    0.16
    Activations Density 0.214%

    No Known Activations