© 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. 13461
    Prev
    Next
    INDEX
    Explanations

    played by or part of

    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
    è¥
    -0.07
     "".
    -0.07
    å½ĵçĦ¶äºĨ
    -0.07
    emarks
    -0.07
    ÅĤas
    -0.06
    ligh
    -0.06
    طاÙĤ
    -0.06
    elaar
    -0.06
    rouw
    -0.06
    è£
    -0.06
    POSITIVE LOGITS
    */)
    0.07
    )':
    0.07
    üst
    0.07
    angguan
    0.07
    为代表çļĦ
    0.06
    rait
    0.06
    '**
    0.06
    GEN
    0.06
    ...'
    0.06
    imus
    0.06
    Activations Density 0.336%

    No Known Activations