© 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. 17725
    Prev
    Next
    INDEX
    Explanations

    existing, known, regard, given, formerly

    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
     frustra
    -0.11
     undermin
    -0.11
    -0.11
     posteri
    -0.11
     deteri
    -0.10
     priorit
    -0.10
     fanta
    -0.10
     assemb
    -0.10
     décadas
    -0.10
     [âĢ¦
    -0.09
    POSITIVE LOGITS
    ,—
    0.09
     chiefly
    0.09
     ;
    0.09
    ,-
    0.09
    ^
    0.09
    ·
    0.08
     pretended
    0.08
     Scotch
    0.08
     furn
    0.08
     particulars
    0.08
    Activations Density 0.712%

    No Known Activations