© 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. 17822
    Prev
    Next
    INDEX
    Explanations

    coracoid, USB, clac

    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
    åħ³éĶ®æĺ¯
    -0.07
    UpDown
    -0.07
    äºİè¡Į
    -0.07
    æľīä»Ģä¹ĪåĮºåĪ«
    -0.07
    çĶŁæ°´
    -0.07
    ÙħÙĪÙĨ
    -0.07
    enso
    -0.07
    ney
    -0.06
    åħ¶ä¸ī
    -0.06
    neys
    -0.06
    POSITIVE LOGITS
     itself
    0.09
    æľ¬èº«
    0.09
    åıĬåħ¶
    0.08
    æĪĸåħ¶
    0.07
    èĩªèº«
    0.07
    æľ¬èº«çļĦ
    0.07
    acom
    0.07
     appunto
    0.07
    åĪ©æµ¦
    0.07
     entirely
    0.07
    Activations Density 0.004%

    No Known Activations