© 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. 20521
    Prev
    Next
    INDEX
    Explanations

    essay assay

    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
    åħ®
    -0.08
    踪
    -0.07
    ower
    -0.07
    elh
    -0.07
    /reference
    -0.07
    POSE
    -0.07
    hout
    -0.07
    tauf
    -0.07
    enance
    -0.07
    ettings
    -0.07
    POSITIVE LOGITS
    éĩĮ
    0.07
    è°ĵä¹ĭ
    0.07
    æ¯Ķæ¯Ķ
    0.07
    称为
    0.07
    åı«åģļ
    0.07
    们çļĦ
    0.06
    udge
    0.06
    antro
    0.06
    ä½³åĵģ
    0.06
    æį¢è¨Ģä¹ĭ
    0.06
    Activations Density 0.111%

    No Known Activations