© 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. 1746
    Prev
    Next
    INDEX
    Explanations

    way too, real problem, only for, restrictive one

    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
    æĭ¥
    -0.07
    æĺ¯ä¸Ń
    -0.07
    èĩ³åħ³
    -0.07
    à¸Ľà¸Ľ
    -0.07
    esp
    -0.07
    اÛĮÙĦ
    -0.07
    alsa
    -0.07
    ades
    -0.07
    éĢıå½»
    -0.07
    ERSHEY
    -0.07
    POSITIVE LOGITS
    çĦī
    0.08
    æįŀåĩº
    0.07
    ingerprint
    0.07
    apia
    0.07
    ä¼ļæĺ¯
    0.07
    æľĥæĺ¯
    0.06
    èĢĮå¦Ĥæŀľ
    0.06
    æĽ´ç¬¦åIJĪ
    0.06
    çĮľæĥ³
    0.06
    çļĦ大å¹ħ
    0.06
    Activations Density 0.009%

    No Known Activations