© 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. 51507
    Prev
    Next
    INDEX
    Explanations

    swap or paste commands

    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
    çIJīçĴĥ
    -0.08
    纶
    -0.07
    ียว
    -0.07
    æ··
    -0.07
    éĹ»è¨Ģ
    -0.07
    abase
    -0.07
    obb
    -0.07
     Bia
    -0.07
    å°¼å°Ķ
    -0.07
     YT
    -0.07
    POSITIVE LOGITS
     Ganz
    0.08
    Ïĩη
    0.07
    æĦıè§ģåıįé¦Ī
    0.07
     cip
    0.07
    è°Ī
    0.07
    uby
    0.06
     jud
    0.06
    ätte
    0.06
    erien
    0.06
    éļıæľº
    0.06
    Activations Density 0.002%

    No Known Activations