© 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. 50318
    Prev
    Next
    INDEX
    Explanations

    mathematical variables

    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
    æľĢåıĹ欢è¿İ
    -0.07
     Bellev
    -0.07
    ÑĢей
    -0.07
    /*/
    -0.07
    uhe
    -0.07
    anean
    -0.07
    æŀģåĬĽ
    -0.07
    Å¡Äį
    -0.07
    Ïĥκε
    -0.07
    ILLE
    -0.07
    POSITIVE LOGITS
    rza
    0.07
     kép
    0.07
    ysis
    0.07
    åĭ¤
    0.06
    <\/
    0.06
     leck
    0.06
    ism
    0.06
    åħĥ
    0.06
    åħĥ人æ°ijå¸ģ
    0.06
    olk
    0.06
    Activations Density 0.017%

    No Known Activations