© 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. 28345
    Prev
    Next
    INDEX
    Explanations

    improper integrals and divergence

    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
    atak
    -0.08
    æĨ¬
    -0.08
    ajor
    -0.08
    memcmp
    -0.08
    è¿·ç³Ĭç³Ĭ
    -0.07
    spell
    -0.07
    andom
    -0.07
     ëĤĺìķĦê°Ģ
    -0.07
     shuffled
    -0.07
    _defaults
    -0.07
    POSITIVE LOGITS
     localized
    0.08
    ugel
    0.08
    uge
    0.07
    对å°ı
    0.07
    éĽĨä¸Ńåľ¨
    0.07
    ê¸ī
    0.07
    å±Ģéĥ¨
    0.07
     concentrated
    0.07
    _locals
    0.07
    ä¸įåIJĪçIJĨ
    0.07
    Activations Density 0.008%

    No Known Activations