© 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. 3220
    Prev
    Next
    INDEX
    Explanations

    names and dates

    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
    éģ
    -0.06
    dro
    -0.06
    ende
    -0.06
     drops
    -0.06
    otá
    -0.06
    ÄĻdzie
    -0.06
     penc
    -0.06
     Chronicle
    -0.06
    çİĩé«ĺ
    -0.06
    æķ°ä¸º
    -0.05
    POSITIVE LOGITS
    ither
    0.09
    å±ħæĺĵ
    0.08
    æĥħåĨµåĪĨæŀIJ
    0.08
    chend
    0.08
     souffle
    0.07
    ATTER
    0.07
    IPHER
    0.07
    lbrace
    0.07
    \\/
    0.07
    ainers
    0.07
    Activations Density 0.098%

    No Known Activations