© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    either or and

    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
    lod
    -0.07
    å¾Ħ
    -0.07
    ÑĦаÑĢ
    -0.07
    ÅĤek
    -0.07
     pomer
    -0.07
    缴å¾Ħ
    -0.07
    wij
    -0.07
    ä¿®éģĵ
    -0.07
     diam
    -0.06
    Setter
    -0.06
    POSITIVE LOGITS
    isex
    0.06
    ahi
    0.06
    ÑĢиÑģÑĤи
    0.06
    alit
    0.06
    jur
    0.06
    ActionResult
    0.06
    梨
    0.06
    åİĭä¸ĭ
    0.06
    çŃīåľºæīĢ
    0.06
    elser
    0.06
    Activations Density 0.131%

    No Known Activations