© 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. 22405
    Prev
    Next
    INDEX
    Explanations

    banana and Panama

    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
    Negative Logits
    eleg
    -0.06
    ä¹ĭ大
    -0.06
    manship
    -0.06
    á»±u
    -0.05
    heart
    -0.05
    严
    -0.05
    quarter
    -0.05
    ÄĻż
    -0.05
    equal
    -0.05
    wolf
    -0.05
    POSITIVE LOGITS
    ilit
    0.07
    ä¾Ŀä¾Ŀ
    0.06
    assed
    0.06
    coni
    0.06
    anjang
    0.05
    abase
    0.05
    /stretch
    0.05
     bananas
    0.05
    меÑĤÑĢов
    0.05
    èĬ¦
    0.05
    Activations Density 0.001%

    No Known Activations