© 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. 39725
    Prev
    Next
    INDEX
    Explanations

    recursion and code structure

    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
    æĬĹéľĩ
    -0.07
    ëijĺ
    -0.07
    yre
    -0.07
    æĻŁ
    -0.07
    _bank
    -0.07
    ired
    -0.07
    fast
    -0.07
    æĺ¯ä¸ĢäºĽ
    -0.06
    integer
    -0.06
    use
    -0.06
    POSITIVE LOGITS
    æĪIJåĬŁåIJİ
    0.08
    æĽ´æ·±
    0.08
     profunda
    0.08
     profund
    0.08
     profonditÃł
    0.08
     deeper
    0.07
    ochond
    0.07
    ackets
    0.07
    è¶Ł
    0.07
     profonda
    0.07
    Activations Density 0.009%

    No Known Activations