© 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. 17916
    Prev
    Next
    INDEX
    Explanations

    modular multiplication

    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
     bl
    -0.07
    éħĴ驾
    -0.07
    çĪµ
    -0.07
    åĸ·å°Ħ
    -0.07
    ä¹ĻéĨĩ
    -0.06
    çļĦé«ĺéĢŁ
    -0.06
    ewood
    -0.06
    ethylene
    -0.06
     Parr
    -0.06
    ä¾Ľ
    -0.06
    POSITIVE LOGITS
    稽
    0.09
    /oauth
    0.09
    Canonical
    0.08
    WithPath
    0.08
    .oauth
    0.08
    canonical
    0.07
    å¦ĸç²¾
    0.07
    ujan
    0.07
    ordes
    0.07
     yoga
    0.07
    Activations Density 0.006%

    No Known Activations