© 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. 24761
    Prev
    Next
    INDEX
    Explanations

    logarithmic formulas and electrical terms

    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
    æĺ¯å¾Īéļ¾
    -0.07
    å¦Ĥæŀľä¸įèĥ½
    -0.07
    以åħįéĢłæĪIJ
    -0.07
    ured
    -0.07
    åı¯èĥ½éĢłæĪIJ
    -0.06
    baugh
    -0.06
    modity
    -0.06
    çĶ±äºİåħ¶
    -0.06
    OutputStream
    -0.06
    æĮijæĪĺæĢ§
    -0.06
    POSITIVE LOGITS
    åı¯æĢľ
    0.08
    oldt
    0.08
    ÛĮ
    0.07
    é¹Ĭ
    0.07
    æĤī
    0.07
    adÃŃ
    0.07
    undle
    0.07
    CLK
    0.07
    ctl
    0.07
    keeper
    0.07
    Activations Density 0.030%

    No Known Activations