© 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. 26498
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ÙĬÙĩ
    -0.07
     Regards
    -0.07
    eping
    -0.07
    èĩ³æѤ
    -0.07
    ette
    -0.07
    etta
    -0.06
    æĤī
    -0.06
     Mois
    -0.06
    æĤ£
    -0.06
    ¾
    -0.06
    POSITIVE LOGITS
    åħ·ä½ĵ
    0.08
    æĪĸèĢħ说
    0.08
    elen
    0.08
    çī¹åĪ«æĺ¯å¯¹
    0.08
    æ¶īåıĬåĪ°
    0.07
    å°¤åħ¶æĺ¯
    0.07
    ilan
    0.07
    iems
    0.07
    æ¶īåıĬ
    0.07
     particularly
    0.07
    Activations Density 0.040%

    No Known Activations