© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29715
    Prev
    Next
    INDEX
    Explanations

    factorial, subsets, binary, protocol

    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
    urin
    -0.08
    å¼łçİī
    -0.07
    iesa
    -0.07
    IMA
    -0.07
    çĭ
    -0.07
    htar
    -0.07
    /chart
    -0.07
    hole
    -0.07
     Centrale
    -0.07
    éĶµ
    -0.07
    POSITIVE LOGITS
    äºĮè¿ĽåĪ¶
    0.09
     bitwise
    0.09
     Boolean
    0.08
     Binary
    0.08
     exponential
    0.08
     togg
    0.08
    Binary
    0.08
     exponentially
    0.07
     binary
    0.07
    binary
    0.07
    Activations Density 0.012%

    No Known Activations