© 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. 43970
    Prev
    Next
    INDEX
    Explanations

    names and numbers

    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
    æĪĸéĥ¨åĪĨ
    -0.07
    éĴµ
    -0.07
    sus
    -0.06
    ä¸Ķ
    -0.06
    riad
    -0.06
    Expression
    -0.06
    åľ°åĪ©
    -0.06
    æľĢåŁºæľ¬
    -0.06
    ä¸Ķä¸į
    -0.06
    ecn
    -0.06
    POSITIVE LOGITS
    XXX
    0.10
     XXX
    0.10
    æŁIJæŁIJ
    0.10
    YYY
    0.10
     xxx
    0.09
    XX
    0.09
     XYZ
    0.08
    XXXX
    0.08
     XX
    0.08
    æĪijåĴĮæĪijçļĦ
    0.08
    Activations Density 0.025%

    No Known Activations