© 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. 30216
    Prev
    Next
    INDEX
    Explanations

    file suffixes

    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
     opi
    -0.07
    çª
    -0.06
    é¹ħ
    -0.06
    ä½łæĪij
    -0.06
    ves
    -0.06
    o
    -0.06
    anta
    -0.06
    eroy
    -0.06
    éĽħ
    -0.06
     tent
    -0.06
    POSITIVE LOGITS
    Ñģел
    0.09
    rna
    0.08
    éĶ¦æ¶Ľ
    0.08
     huk
    0.08
    ánh
    0.08
    PMC
    0.07
    çĥģ
    0.07
    athed
    0.07
    ¿
    0.07
    第ä¸ĢæľŁ
    0.07
    Activations Density 0.387%

    No Known Activations