© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38559
    Prev
    Next
    INDEX
    Explanations

    code snippets with attributes

    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
    mb
    -0.07
     ``(
    -0.06
    Âł
    -0.06
     kin
    -0.06
    Tre
    -0.06
     Ø«
    -0.05
    (/
    -0.05
    æī¹
    -0.05
    ↵
    -0.05
    ä¸ĢåĪ»
    -0.05
    POSITIVE LOGITS
    vera
    0.08
    èĪįåĪ©
    0.08
    irme
    0.08
    edException
    0.08
    éĿĵ
    0.08
    åĺĽ
    0.08
    天ä¹ĭ
    0.07
     zufolge
    0.07
    ulumi
    0.07
    trz
    0.07
    Activations Density 0.014%

    No Known Activations