© 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. 60800
    Prev
    Next
    INDEX
    Explanations

    mathematical function definitions

    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
     ste
    -0.07
    èĥĨåŃIJ
    -0.06
    éĻIJäºİ
    -0.06
    æĻ¶
    -0.06
    vsp
    -0.06
    æķħäºĭæĥħ
    -0.06
    mort
    -0.06
    YSTEM
    -0.06
    è¿°
    -0.06
    _
    -0.06
    POSITIVE LOGITS
    æIJĶ
    0.08
    iken
    0.07
    åŃļ
    0.07
    anced
    0.07
    वन
    0.07
    æĮīçħ§åĽ½å®¶
    0.07
    own
    0.07
    Delimiter
    0.07
    _forms
    0.07
    bach
    0.07
    Activations Density 0.138%

    No Known Activations