© 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. 20903
    Prev
    Next
    INDEX
    Explanations

    log and ln functions

    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
    ognito
    -0.07
    æĥħåĨµåĪĨæŀIJ
    -0.06
    åŃ¦ä¹łä»»åĬ¡
    -0.06
     ||=
    -0.06
    /o
    -0.06
    oyo
    -0.06
    oe
    -0.06
    å·¥ä½ľæĥħåĨµ
    -0.06
    ooth
    -0.06
    asaki
    -0.06
    POSITIVE LOGITS
    Äįen
    0.08
    junk
    0.08
    lint
    0.07
    ếc
    0.07
    Äįit
    0.07
    åĴĮçĽijçĿ£
    0.07
    CLOCKS
    0.07
    çĹĽå¿«
    0.07
    =log
    0.07
    åIJŀåIJIJ
    0.07
    Activations Density 0.001%

    No Known Activations