© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20608
    Prev
    Next
    INDEX
    Explanations

    academic journals and publications

    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
    æ¯ı天æľī
    -0.08
    kota
    -0.07
    çĶ©
    -0.07
     вело
    -0.07
    æ¯ı天
    -0.07
    æ¯ı天éĥ½æľī
    -0.07
     daily
    -0.07
    åħ¬è½¦
    -0.07
    ieux
    -0.07
    esso
    -0.07
    POSITIVE LOGITS
    建åĪ¶
    0.07
    åı¯æĢľçļĦ
    0.07
    imeo
    0.07
    ائ
    0.07
     благо
    0.07
    isy
    0.07
    andler
    0.06
    chema
    0.06
     Friendship
    0.06
    好åŃ©åŃIJ
    0.06
    Activations Density 0.008%

    No Known Activations