© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32231
    Prev
    Next
    INDEX
    Explanations

    Exemplo, minute, edits, update, re-edit

    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
    ¯
    -0.08
    ²
    -0.08
    tritt
    -0.08
    oge
    -0.07
    ogi
    -0.07
    æ²ī
    -0.07
    azz
    -0.07
    æĺ¯ä¸Ģé¢Ĺ
    -0.07
    earn
    -0.07
    uego
    -0.07
    POSITIVE LOGITS
    ä¸ĭæĸĩ
    0.08
    漪
    0.07
    åIJģ
    0.06
    æĪIJæľ¬æݧåĪ¶
    0.06
    åħ¶ä¹IJ
    0.06
    akwa
    0.06
    _py
    0.06
    inh
    0.06
    ئÙĥ
    0.06
    _mt
    0.06
    Activations Density 0.014%

    No Known Activations