© 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. 14706
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or choices

    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
    defaults
    -0.07
     /*#__
    -0.07
    ìĨį
    -0.07
     Untersch
    -0.07
     Hass
    -0.06
    tt
    -0.06
    .utility
    -0.06
    hait
    -0.06
    tese
    -0.06
    ãĤŃãĤµ
    -0.06
    POSITIVE LOGITS
    éĢ¢
    0.08
    -feed
    0.07
    åıijçĶŁéĩį大
    0.07
    atera
    0.07
    enheim
    0.07
    ifiable
    0.07
    ilated
    0.07
    uru
    0.07
    fy
    0.07
    æĹłéĻIJçļĦ
    0.07
    Activations Density 0.059%

    No Known Activations