© 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. 16887
    Prev
    Next
    INDEX
    Explanations

    Continue reading

    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
    å¾Ĺä¸Ĭ
    -0.06
    ply
    -0.06
     xuyên
    -0.05
    éĥijéĩį声æĺİ
    -0.05
     Actual
    -0.05
    æ·ĺæ±°
    -0.05
     ê²°ìłķ
    -0.05
     uncomp
    -0.05
     deeper
    -0.05
    ÑĨÑı
    -0.05
    POSITIVE LOGITS
    åł¤
    0.06
    Ñĩем
    0.06
    äºĭåıij
    0.06
    emis
    0.05
    antine
    0.05
    egin
    0.05
    azza
    0.05
    tease
    0.05
    èĢĮæѤæŶ
    0.05
     promosso
    0.05
    Activations Density 0.001%

    No Known Activations