© 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. 14602
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols with letters

    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
    ↵
    -0.07
    °.
    -0.07
    ++.
    -0.06
    Ñĩами
    -0.06
    çŃīçŃī
    -0.06
    èĢĮå¾ĹåIJį
    -0.06
    d
    -0.06
    ame
    -0.06
    âĤ¬.
    -0.06
    令第
    -0.06
    POSITIVE LOGITS
     bukanlah
    0.09
    çļĦè¯Ħä»·æĺ¯
    0.08
    æ±Ĥæĺ¯
    0.08
     konusu
    0.08
    0.07
    andler
    0.07
    åħīæĺ¯
    0.07
    Ĥ¹
    0.07
    Qed
    0.07
    .xx
    0.07
    Activations Density 0.025%

    No Known Activations