© 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. 48699
    Prev
    Next
    INDEX
    Explanations

    and the

    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
    úc
    -0.07
    ÃŃb
    -0.07
    -svg
    -0.06
    apter
    -0.06
    港澳åı°
    -0.06
    åħ¬ä»Ķ
    -0.06
    ä»İæĪijåģļèµ·
    -0.06
    blas
    -0.06
    åĪ«æł·
    -0.06
    ongan
    -0.06
    POSITIVE LOGITS
    odat
    0.07
    abit
    0.07
    otec
    0.06
    otka
    0.06
    ++.
    0.06
    ä¸ŃæĸĩåIJį
    0.06
     tyle
    0.06
     ::=
    0.06
     Suns
    0.06
    echsl
    0.06
    Activations Density 0.037%

    No Known Activations