© 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. 63781
    Prev
    Next
    INDEX
    Explanations

    U. or She or Below or Unlike or Timothy

    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
    endl
    -0.09
    refs
    -0.07
    _then
    -0.07
    otos
    -0.07
    cents
    -0.07
    ibl
    -0.07
    ,right
    -0.07
    ÏĦαι
    -0.06
    cart
    -0.06
    åĪĨ享åĪ°
    -0.06
    POSITIVE LOGITS
    åı¦å¤ĸ
    0.07
    æѤå¤ĸ
    0.06
    ingu
    0.06
    alay
    0.06
    ump
    0.06
    aby
    0.06
    åħ»
    0.06
    èģŀ
    0.06
    uz
    0.06
    erk
    0.06
    Activations Density 0.636%

    No Known Activations