© 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. 7690
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è¿İ
    -0.08
    önt
    -0.07
    åľĨåľĨçļĦ
    -0.07
    æł¼ä¸½
    -0.07
    ÑĤÑĬ
    -0.07
    aira
    -0.07
    ÄIJT
    -0.07
    yny
    -0.07
    éĹ·
    -0.07
    toi
    -0.07
    POSITIVE LOGITS
    cers
    0.07
    ighbors
    0.06
    éĥ¨éŨ
    0.06
     أض
    0.06
    大æ¦Ĥ
    0.06
    ³
    0.06
    ."/
    0.06
    ably
    0.06
    angs
    0.06
    uh
    0.06
    Activations Density 0.000%

    No Known Activations