© 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. 21550
    Prev
    Next
    INDEX
    Explanations

    layouts and designs

    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
     Belmont
    -0.07
     (*((
    -0.06
     escal
    -0.06
    Introduced
    -0.06
    rgan
    -0.06
    主è¦ģæĺ¯æĮĩ
    -0.06
    odox
    -0.06
    aises
    -0.06
    cou
    -0.06
     scaling
    -0.06
    POSITIVE LOGITS
    Sortable
    0.10
    åIJİç¼Ģ
    0.09
    æ§ĭ
    0.09
    suffix
    0.08
    è´ª
    0.08
    åī©ä½Ļ
    0.08
    é«ĺé«ĺ
    0.08
     greed
    0.08
     greedy
    0.08
    å°½éĩı
    0.08
    Activations Density 0.001%

    No Known Activations