© 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. 17663
    Prev
    Next
    INDEX
    Explanations

    appendix or appendices

    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
    å½ĵåħ¶
    -0.07
    éc
    -0.07
    åĩºæ°´
    -0.07
    νε
    -0.07
    noinspection
    -0.07
     uphill
    -0.06
    ç¢ĹéĩĮ
    -0.06
    forsch
    -0.06
    kring
    -0.06
    æĹ¢è¦ģ
    -0.06
    POSITIVE LOGITS
     appendix
    0.10
     useful
    0.09
     Useful
    0.09
     Appendix
    0.09
    Append
    0.09
    æľīçĶ¨çļĦ
    0.08
    éĻĦå½ķ
    0.08
    append
    0.08
    大åĪ°
    0.08
    ovnÃŃ
    0.08
    Activations Density 0.031%

    No Known Activations