© 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. 50336
    Prev
    Next
    INDEX
    Explanations

    other items or continuing after

    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
    ought
    -0.07
    irut
    -0.07
    ewire
    -0.07
    aghetti
    -0.07
    ambang
    -0.07
    éĩıå°ij
    -0.07
    è¾¾æĭī
    -0.06
    ç´§å¼łçļĦ
    -0.06
    æĭĤ
    -0.06
    æī§è¡Į人
    -0.06
    POSITIVE LOGITS
    -other
    0.10
     sonst
    0.09
    åĪ°åħ¶ä»ĸ
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    åħ¶ä½Ļ
    0.09
    åħ¶é¤ĺ
    0.09
    çļĦåħ¶ä»ĸ
    0.09
    åħ¶ä»ĸåľ°æĸ¹
    0.08
    other
    0.08
    åħ¶ä»ĸ
    0.08
    Activations Density 0.106%

    No Known Activations