© 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. 48313
    Prev
    Next
    INDEX
    Explanations

    code including imports

    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
    è§ģå¾Ĺ
    -0.08
    èĩ³åħ³
    -0.07
    责任ç¼ĸè¾ij
    -0.07
     memp
    -0.07
    تÙħاÙĨ
    -0.07
    uenta
    -0.07
    ointments
    -0.07
    hound
    -0.07
    áŁĤ
    -0.07
    åĵį声
    -0.07
    POSITIVE LOGITS
    iza
    0.08
    ets
    0.07
    изи
    0.07
    çIJ¦
    0.07
    ics
    0.07
    ora
    0.07
    tt
    0.07
    lott
    0.06
    izio
    0.06
    aim
    0.06
    Activations Density 0.001%

    No Known Activations