© 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. 64009
    Prev
    Next
    INDEX
    Explanations

    information about handling

    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
    ÑĤовÑĭй
    -0.07
    sti
    -0.07
    æľĢæĸ°æĽ´æĸ°
    -0.06
    éĤ£ä»ĸ
    -0.06
     And
    -0.06
    ä½Ĩæĺ¯æĪij
    -0.06
     Plus
    -0.06
    ime
    -0.06
    è´¸
    -0.06
    then
    -0.06
    POSITIVE LOGITS
    /ion
    0.08
    <ul
    0.08
    åħ¬åı¸å°Ĩ
    0.07
    ãĥĿãĤ¤ãĥ³ãĥĪãģ¯
    0.07
     -:
    0.07
    éĻ¤äºĨè¦ģ
    0.07
    åħ¥å¾®
    0.07
    acÄĥ
    0.07
    ounc
    0.07
     ãĥ»
    0.07
    Activations Density 0.021%

    No Known Activations