© 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. 17311
    Prev
    Next
    INDEX
    Explanations

    length constraint

    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
    PACK
    -0.06
    pack
    -0.06
     packing
    -0.06
    oug
    -0.06
     remaining
    -0.06
     pak
    -0.06
    æĹłè®ºä½ł
    -0.06
    è¾ĥéĩį
    -0.05
    太éĩį
    -0.05
    è§ģä»ĸ
    -0.05
    POSITIVE LOGITS
    orm
    0.06
    atal
    0.06
     Tops
    0.05
    éĨį
    0.05
    ä¸ĢåŃĹ
    0.05
    va
    0.05
    -lang
    0.05
    odont
    0.05
    vos
    0.05
    vall
    0.05
    Activations Density 0.003%

    No Known Activations