© 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. 18742
    Prev
    Next
    INDEX
    Explanations

    email newsletter days

    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
    åħ·
    -0.07
    æv
    -0.07
    ụn
    -0.07
    å¼Ĥåľ°
    -0.07
    ÑģовеÑģÑĤ
    -0.07
    ำ
    -0.07
     scu
    -0.07
    ser
    -0.07
    à¬
    -0.06
    erenc
    -0.06
    POSITIVE LOGITS
    olling
    0.08
    (fin
    0.07
    åIJįåĪ©
    0.07
    ä¸Ģå¤ķ
    0.07
    ASIL
    0.07
    latt
    0.07
    (att
    0.06
    ,Th
    0.06
    éħ£
    0.06
    为æķ°
    0.06
    Activations Density 0.012%

    No Known Activations