© 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. 51449
    Prev
    Next
    INDEX
    Explanations

    Requestby0

    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
    Typed
    -0.06
    ÏĦαÏĤ
    -0.06
    aterno
    -0.06
    ä½ľåĪĻ
    -0.06
    eref
    -0.06
    è¿ĩå±±
    -0.06
    anke
    -0.06
    ião
    -0.06
    æ°ĵ
    -0.06
    uiten
    -0.06
    POSITIVE LOGITS
    ุà¹Īม
    0.07
    çĴĢ
    0.07
     Tam
    0.06
    ÃŃts
    0.06
    CP
    0.06
    æĸ¯åį¡
    0.06
    inton
    0.06
    è´¹å°Ķ
    0.06
    umon
    0.06
    _bs
    0.06
    Activations Density 0.146%

    No Known Activations