© 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. 55761
    Prev
    Next
    INDEX
    Explanations

    free magnetic

    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
    梧
    -0.06
    aug
    -0.06
    /W
    -0.06
     Tam
    -0.06
    æĭ¥
    -0.06
    lec
    -0.06
     fault
    -0.06
    æݸ
    -0.06
     полов
    -0.06
     Flynn
    -0.05
    POSITIVE LOGITS
    迪äºļ
    0.09
    ialog
    0.08
    onga
    0.08
     ÐĹаÑĤо
    0.08
    escription
    0.08
    纯粹
    0.08
    SRC
    0.08
     purely
    0.08
    åıªåī©
    0.08
    åıªåī©ä¸ĭ
    0.07
    Activations Density 0.031%

    No Known Activations