© 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. 61847
    Prev
    Next
    INDEX
    Explanations

    adding ingredients or steps

    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
    ucar
    -0.09
    åĩºä¸į
    -0.07
    亲è¿ij
    -0.06
     deleted
    -0.06
    Damage
    -0.06
    _crop
    -0.06
    常åIJĥ
    -0.06
    æĪĸ缺
    -0.06
    ä¸ĢæľĿ
    -0.06
     Cerc
    -0.06
    POSITIVE LOGITS
    ç¼ĵç¼ĵ
    0.10
    éĢIJ
    0.09
     slowly
    0.09
    ç¼ĵç¼ĵåľ°
    0.09
    æħ¢æħ¢
    0.09
     gradually
    0.09
    ç¼ĵç¼ĵçļĦ
    0.09
    ç¼ĵæħ¢
    0.08
    æħ¢æħ¢åľ°
    0.08
    åIJİç«ĭåį³
    0.08
    Activations Density 0.036%

    No Known Activations