© 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. 15185
    Prev
    Next
    INDEX
    Explanations

    0, 1, a, b, n

    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
    (~
    -0.07
    eka
    -0.06
    amic
    -0.06
    alc
    -0.06
    resse
    -0.06
    .:
    -0.06
    lessly
    -0.06
    ä¼ĺå¼ĤçļĦæĪIJ绩
    -0.06
    æĥħ人
    -0.06
    vid
    -0.06
    POSITIVE LOGITS
    gether
    0.09
    <|box_end|>
    0.08
    armi
    0.08
    èĮĥåĽ´ä¹ĭåĨħ
    0.08
    èĩªå·±èº«ä¸Ĭ
    0.08
    ições
    0.08
    çī¹æĸ¯
    0.07
    çİīå±±
    0.07
    ä¸ĭåIJĮ
    0.07
    ä¹ĭåĪĹ
    0.07
    Activations Density 0.002%

    No Known Activations