© 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. 10632
    Prev
    Next
    INDEX
    Explanations

    approach to a problem

    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
    Äįenje
    -0.09
    urgia
    -0.09
    rosa
    -0.09
     повÑĸд
    -0.08
    nier
    -0.08
    ordu
    -0.08
    çªŁ
    -0.08
    izens
    -0.08
    ActionCode
    -0.08
    ambul
    -0.08
    POSITIVE LOGITS
    åĪ°çļĦ
    0.11
    able
    0.08
    pend
    0.08
    es
    0.07
    оÑĤÑĢе
    0.07
    ÙĨÚ¯
    0.07
    vement
    0.07
    ulse
    0.06
    ments
    0.06
    (es
    0.06
    Activations Density 0.032%

    No Known Activations