© 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. 29357
    Prev
    Next
    INDEX
    Explanations

    location :

    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
    ansas
    -0.08
    éģ¥éģ¥
    -0.07
    moid
    -0.07
    itten
    -0.07
    unjuk
    -0.07
    åı¯ä»¥åĪ°
    -0.07
    zeni
    -0.07
    lust
    -0.06
    ugn
    -0.06
    ascii
    -0.06
    POSITIVE LOGITS
    åĩ½æķ°çļĦ
    0.08
    ä¸Ģåħĥ
    0.07
    vale
    0.07
    åĩ½æķ°
    0.07
    å®ŀ
    0.07
    æ±Ĥå®ŀ
    0.07
    bole
    0.07
    quilla
    0.07
     xs
    0.06
    ayan
    0.06
    Activations Density 0.003%

    No Known Activations