© 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. 22929
    Prev
    Next
    INDEX
    Explanations

    web browser link

    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
    mdl
    -0.08
    ıl
    -0.07
    apak
    -0.07
    fus
    -0.07
    ael
    -0.07
    åįĥç§ĭ
    -0.07
    ocere
    -0.06
    FX
    -0.06
    ä¸ļåĬ¡æĶ¶åħ¥
    -0.06
    ANTE
    -0.06
    POSITIVE LOGITS
    ä¸įæĺİçĻ½
    0.09
    ROID
    0.07
    éļ¾æ±Ĥ
    0.07
    ersch
    0.07
    åĴĮè°ĥæķ´
    0.07
     hala
    0.07
    aryana
    0.07
    )did
    0.07
    aries
    0.06
    anya
    0.06
    Activations Density 0.002%

    No Known Activations