© 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. 63932
    Prev
    Next
    INDEX
    Explanations

    model field definitions

    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
    ooks
    -0.08
    ToStr
    -0.08
    bane
    -0.07
    Äģk
    -0.07
    før
    -0.07
     Ø£ÙĨØŃاء
    -0.07
    itage
    -0.07
    à¸Ĭืà¹Īà¸Ńวà¹Īา
    -0.07
    occhi
    -0.07
    Rol
    -0.07
    POSITIVE LOGITS
    Mutable
    0.07
    æī¹ç¤º
    0.07
    ucha
    0.07
    دÙĬÙĦ
    0.06
    kh
    0.06
    ator
    0.06
    åı¦ä¸Ģ
    0.06
    æľį
    0.06
    atus
    0.06
    LP
    0.06
    Activations Density 0.132%

    No Known Activations