© 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. 23085
    Prev
    Next
    INDEX
    Explanations

    publication years and other details

    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
    irse
    -0.07
    oshi
    -0.07
    çĤºæѤ
    -0.06
    oral
    -0.06
    èĢģå¸Ī说
    -0.06
    áng
    -0.06
    ommel
    -0.06
     اÙģرادÛĮ
    -0.06
    “They
    -0.06
    èĬ±å¼ı
    -0.06
    POSITIVE LOGITS
     vols
    0.08
     reprint
    0.08
    isbn
    0.07
    åĩºçīĪæŶéĹ´
    0.07
    è¢ĸ
    0.07
    ISBN
    0.07
    ervations
    0.07
    _translation
    0.07
    lp
    0.07
    _DMA
    0.07
    Activations Density 0.073%

    No Known Activations