© 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. 62377
    Prev
    Next
    INDEX
    Explanations

    a/an followed by abstract nouns

    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
    omb
    -0.08
    deal
    -0.07
    åłª
    -0.07
    zen
    -0.07
    ombo
    -0.07
    keit
    -0.07
    onte
    -0.07
    æıĴä¸Ĭ
    -0.07
    身边
    -0.07
    ten
    -0.07
    POSITIVE LOGITS
    acons
    0.08
     bona
    0.07
    è··
    0.07
    ä½łåĪ°åºķ
    0.07
    Defines
    0.06
    enek
    0.06
    Æ°a
    0.06
     albeit
    0.06
    VERR
    0.06
    stro
    0.06
    Activations Density 0.021%

    No Known Activations