© 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. 16586
    Prev
    Next
    INDEX
    Explanations

    slippery surfaces and grip

    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
    èµ´ç¾İ
    -0.06
    ndon
    -0.06
    schnitt
    -0.06
    ÙĪت
    -0.06
    æīĵçļĦ
    -0.06
     اÙĦÙĦÙĩÙı
    -0.06
    /Gate
    -0.06
    溺
    -0.05
    ombongan
    -0.05
    é¢IJ
    -0.05
    POSITIVE LOGITS
    éĺ²æ»ij
    0.06
     tar
    0.06
    æ¿Ģæ´»
    0.06
    强
    0.06
     slipping
    0.06
     slippery
    0.05
     activating
    0.05
     activation
    0.05
     awakening
    0.05
     lul
    0.05
    Activations Density 0.024%

    No Known Activations