© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60103
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

    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
    ç»ĥ
    -0.06
    us
    -0.06
    æĮ½
    -0.06
    rog
    -0.06
    ulle
    -0.06
     reli
    -0.06
     efe
    -0.06
     ØŃاÙĦÛĮ
    -0.06
    "
    -0.06
    ane
    -0.06
    POSITIVE LOGITS
    å©ķ
    0.10
    ---</
    0.09
    éĢłåĮĸ
    0.08
    optgroup
    0.07
    ILED
    0.07
    onos
    0.07
    etheless
    0.07
    ¶
    0.07
    ãĢħ
    0.07
    æ¢ħæŀĹ
    0.07
    Activations Density 0.006%

    No Known Activations