© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18673
    Prev
    Next
    INDEX
    Explanations

    number registration

    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
    æĹ¢æľī
    -0.06
    _inter
    -0.05
    atter
    -0.05
    anch
    -0.05
     Re
    -0.05
     ÙħÙĨÙĩا
    -0.05
    伤å¿ĥ
    -0.05
     terminal
    -0.05
    éĢĤæŶ
    -0.05
    abs
    -0.05
    POSITIVE LOGITS
    ancock
    0.06
    gede
    0.06
    认è¯Ĩ
    0.06
    icca
    0.06
    meen
    0.06
     renvo
    0.06
    inite
    0.06
    éŁ³
    0.06
     whatsoever
    0.05
    adden
    0.05
    Activations Density 0.001%

    No Known Activations