© 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. 1218
    Prev
    Next
    INDEX
    Explanations

    citations and academic references

    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
    ...
    -0.07
    +
    -0.06
    /
    -0.06
    ä¸ĩå²ģ
    -0.06
    \"
    -0.06
    âĢ¦
    -0.06
    loff
    -0.06
    åı£
    -0.06
     -
    -0.06
    agi
    -0.05
    POSITIVE LOGITS
    !!:
    0.09
    WithType
    0.09
    adar
    0.08
    ehold
    0.08
    ajter
    0.08
    egah
    0.08
    ICAST
    0.08
    NullOrEmpty
    0.08
    ä½łæĺ¯æĪijçļĦ
    0.08
    ilib
    0.08
    Activations Density 0.019%

    No Known Activations