© 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. 8926
    Prev
    Next
    INDEX
    Explanations

    intermediate compounds and products

    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
     Ende
    -0.08
    FFE
    -0.07
    icana
    -0.07
    utkan
    -0.07
    å®ħ
    -0.07
    utan
    -0.06
    inka
    -0.06
    acor
    -0.06
    å¹´åįİ
    -0.06
    .walk
    -0.06
    POSITIVE LOGITS
     intermediate
    0.12
    Intermediate
    0.11
     Intermediate
    0.11
     intermediary
    0.09
     intermedi
    0.09
    éĺ¶æ®µæĢ§
    0.08
    ä¸ŃæľŁ
    0.08
    ä¸ŃéĹ´
    0.08
     interim
    0.08
    ather
    0.08
    Activations Density 0.024%

    No Known Activations