© 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. 9459
    Prev
    Next
    INDEX
    Explanations

    available spaces

    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
    heim
    -0.08
    ç»ķ
    -0.07
    è§Ĥ
    -0.07
    åħ°çī¹
    -0.07
    åIJ«
    -0.07
    åĬªåĬĽåģļåĪ°
    -0.06
    æºIJåľ°
    -0.06
     verz
    -0.06
     boxed
    -0.06
    ä¸ŃåIJ«
    -0.06
    POSITIVE LOGITS
    วà¹Īาà¸ĩ
    0.15
    容纳
    0.14
     space
    0.14
     reserved
    0.14
     vacant
    0.13
     available
    0.13
    空éĹ´
    0.13
    空éĹ´çļĦ
    0.13
    available
    0.13
    空éĹ´åĴĮ
    0.13
    Activations Density 0.279%

    No Known Activations