© 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. 14206
    Prev
    Next
    INDEX
    Explanations

    indirect or indirectly

    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
    ioneer
    -0.08
    ä¸įåīį
    -0.08
    ilde
    -0.08
    acious
    -0.07
    laut
    -0.07
    ekom
    -0.07
    leveland
    -0.07
     irrespective
    -0.07
    osit
    -0.07
    noinspection
    -0.07
    POSITIVE LOGITS
    éĹ´æİ¥
    0.13
    æĪĸ缴æİ¥
    0.11
    ëĤĺë§Ī
    0.11
     indire
    0.11
     indirect
    0.10
     módon
    0.09
     indirectly
    0.09
     poÅĽred
    0.08
     INDIRECT
    0.08
    irect
    0.08
    Activations Density 0.014%

    No Known Activations