© 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. 2311
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    addon
    -0.08
    jaht
    -0.07
    kees
    -0.07
    gui
    -0.07
     corri
    -0.07
    arket
    -0.07
    riu
    -0.07
    arly
    -0.07
    оÑģÑĥ
    -0.07
    “Yes
    -0.07
    POSITIVE LOGITS
    é¡¹çĽ®è¿Ľè¡Į
    0.07
    finite
    0.07
    æ¸į
    0.07
    ë§Į
    0.07
     Motel
    0.06
    éĻĦè¿ijæľī
    0.06
    æĬijåĪ¶åīĤ
    0.06
    ´
    0.06
    好åķĬ
    0.06
    fin
    0.06
    Activations Density 0.053%

    No Known Activations