© 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. 22859
    Prev
    Next
    INDEX
    Explanations

    derivative computation

    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
     téléphonique
    -0.08
    /vendors
    -0.07
    æľĶ
    -0.07
    èĵ¬åĭĥ
    -0.07
    è¶ħéĩį
    -0.07
    íĢĦ
    -0.07
    ä¸īéĿ¢
    -0.07
    å¹
    -0.07
    emente
    -0.07
    ucid
    -0.07
    POSITIVE LOGITS
     Pol
    0.07
    oden
    0.06
    xf
    0.06
    <![
    0.06
     “
    0.06
     pol
    0.06
     du
    0.06
     sob
    0.06
     handle
    0.06
     SCE
    0.06
    Activations Density 0.012%

    No Known Activations