© 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. 14525
    Prev
    Next
    INDEX
    Explanations

    importance, concern, issue, topic

    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
    istem
    -0.08
    åĨį说äºĨ
    -0.08
    omid
    -0.07
    ertas
    -0.07
    igl
    -0.07
    ?$
    -0.07
    xmlns
    -0.07
    als
    -0.07
     Medina
    -0.07
    stras
    -0.06
    POSITIVE LOGITS
    Readable
    0.09
    åħ³ä¹İ
    0.08
    å®ŀéĻħéľĢæ±Ĥ
    0.07
    å®īåħ¨éĹ®é¢ĺ
    0.07
    马èĻİ
    0.07
    æıª
    0.07
     enje
    0.07
    .ser
    0.07
     practical
    0.07
    æľįåĬ¡éĥ¨
    0.07
    Activations Density 0.185%

    No Known Activations