© 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. 9700
    Prev
    Next
    INDEX
    Explanations

    could use

    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
    uh
    -0.07
    nbr
    -0.07
     Carey
    -0.06
    ovsky
    -0.06
     "
    -0.06
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    -0.06
    产åĵģä¸Ńå¿ĥ
    -0.06
    已形æĪIJ
    -0.06
    èĭĽåĪ»
    -0.06
    sic
    -0.06
    POSITIVE LOGITS
    åı¸
    0.08
    igy
    0.07
    áĢĿ
    0.07
    éĥ½æľīåĵªäºĽ
    0.07
    ereo
    0.07
    ä¸īåı·
    0.07
    lesa
    0.07
    ULLET
    0.07
    audi
    0.07
    asher
    0.07
    Activations Density 0.026%

    No Known Activations