© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16829
    Prev
    Next
    INDEX
    Explanations

    user experience and interaction design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ØŃÙħ
    -0.06
     Bale
    -0.06
    bol
    -0.06
     shredd
    -0.06
    æĵįä½ľä¸Ĭ
    -0.06
    head
    -0.06
     bol
    -0.06
    accio
    -0.05
     signature
    -0.05
    شتÙĩ
    -0.05
    POSITIVE LOGITS
    اÙĨÙĪÙĨ
    0.06
    repub
    0.05
    mitt
    0.05
    åħĪ
    0.05
     abducted
    0.05
     grounded
    0.05
     conson
    0.05
     neu
    0.05
    adb
    0.05
     grounding
    0.05
    Activations Density 0.010%

    No Known Activations