© 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. 48274
    Prev
    Next
    INDEX
    Explanations

    movement through

    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
    éļıå¤Ħ
    -0.08
    祸é¦ĸ
    -0.08
    é£ŁãģĦ
    -0.07
    iled
    -0.07
    _sources
    -0.07
    erad
    -0.07
    iped
    -0.07
    ilik
    -0.07
    indet
    -0.07
    ideo
    -0.07
    POSITIVE LOGITS
     мимо
    0.13
     melewati
    0.11
    èĢĮè¿ĩ
    0.11
    éļ¾åħ³
    0.11
     passes
    0.10
    æĹłéĺ»
    0.10
    ç©¿è¿ĩ
    0.10
     passing
    0.09
    /pass
    0.09
    ogh
    0.09
    Activations Density 0.093%

    No Known Activations