© 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. 46739
    Prev
    Next
    INDEX
    Explanations

    any (followed by noun/adjective)

    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
    ç¿Ķ
    -0.08
    erset
    -0.08
    çĮĸ
    -0.08
    urts
    -0.07
    æĺ¯åĢ¼å¾Ĺ
    -0.07
    å¾Īå¤ļåľ°æĸ¹
    -0.07
    estig
    -0.07
    agas
    -0.07
     Olah
    -0.07
    åģıåģı
    -0.07
    POSITIVE LOGITS
     évent
    0.10
     remaining
    0.10
     potential
    0.08
     eventuali
    0.08
    remaining
    0.08
    /all
    0.08
     necessary
    0.08
     applicable
    0.08
     needed
    0.08
    åı¯èĥ½çļĦ
    0.08
    Activations Density 0.181%

    No Known Activations