© 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. 32459
    Prev
    Next
    INDEX
    Explanations

    resources and links

    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
    ä¸įèĥ½æľī
    -0.07
    æłĩåĩĨè¦ģæ±Ĥ
    -0.06
    æĥŃ
    -0.06
     athleticism
    -0.06
    çĮľæĥ³
    -0.06
    ä¸įæ¸ħ
    -0.06
    énk
    -0.06
    çľģçķ¥
    -0.06
    ä»Ģä¹ĪåİŁåĽł
    -0.06
    ä¸Ģä½ľ
    -0.06
    POSITIVE LOGITS
     available
    0.11
     resources
    0.10
    available
    0.10
    çļĦ好åİ»å¤Ħ
    0.10
    æݨèįIJçļĦ
    0.10
    æݨèįIJ
    0.10
    resources
    0.09
    åı¯ä»¥å¸®åĬ©ä½ł
    0.09
    åı¯ä»¥æī¾åĪ°
    0.09
     ressources
    0.09
    Activations Density 0.459%

    No Known Activations