© 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. 17098
    Prev
    Next
    INDEX
    Explanations

    yet to + [verb]

    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
    ically
    -0.08
    iewicz
    -0.08
    SHIP
    -0.08
    -quarters
    -0.07
    aliz
    -0.07
    aré
    -0.07
    ation
    -0.07
    ugh
    -0.07
    ovid
    -0.07
    åĢij
    -0.06
    POSITIVE LOGITS
    çŁ¥çļĦ
    0.10
    æľīä»»ä½ķ
    0.09
    å°Ŀä¸įæĺ¯
    0.09
    usal
    0.09
    çĦ¶æĺ¯
    0.09
    assel
    0.09
    ropolit
    0.08
    ãģªãĤīãģļ
    0.08
    çĶļèĢħ
    0.08
    irchen
    0.08
    Activations Density 0.007%

    No Known Activations