© 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. 14142
    Prev
    Next
    INDEX
    Explanations

    move, search, reproduce, scan

    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
    odian
    -0.07
    otte
    -0.06
    ondi
    -0.06
    ãģ«åħ¥ãģ£ãģ¦
    -0.06
    Ïĥή
    -0.06
    ×Ļ×ķתר
    -0.06
    jek
    -0.06
    iled
    -0.05
    pe
    -0.05
    isset
    -0.05
    POSITIVE LOGITS
    两ä¸į误
    0.10
    ä¸Ģä½ĵæľº
    0.08
    ¹Ħ
    0.07
    slag
    0.07
    ingga
    0.07
    æļ
    0.07
    (IB
    0.07
    entifier
    0.07
    人è´Ńä¹°
    0.07
    ä¹ĭäºĭ
    0.07
    Activations Density 0.050%

    No Known Activations