© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17776
    Prev
    Next
    INDEX
    Explanations

    infinite, unlimited, and boundless concepts

    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
    ellido
    -0.06
    helper
    -0.06
     Artis
    -0.06
    ç»ĵæĿŁ
    -0.05
     lesser
    -0.05
    hão
    -0.05
    ãĤ¨ãĥ³ãĥī
    -0.05
     minor
    -0.05
    Minor
    -0.05
    Isl
    -0.05
    POSITIVE LOGITS
     infinite
    0.09
     unlimited
    0.09
     limitless
    0.08
     Infinite
    0.08
     Unlimited
    0.08
    æĹłéĻIJ
    0.08
     indefinite
    0.07
    finite
    0.07
    æľīéĻIJ
    0.07
     finite
    0.07
    Activations Density 0.087%

    No Known Activations