© 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. 21707
    Prev
    Next
    INDEX
    Explanations

    section markers

    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
    ocen
    -0.07
    jedn
    -0.07
     kath
    -0.07
    å·²åĶ®
    -0.06
     лиÑĨе
    -0.06
     vri
    -0.06
    å¦ĤçĥŁ
    -0.06
    è¾ľ
    -0.06
     vui
    -0.06
    éĿ¢ç§¯è¾¾
    -0.06
    POSITIVE LOGITS
    0.05
    ar
    0.05
    ↵
    0.05
     either
    0.05
    amped
    0.05
    .
    0.05
     --
    0.05
     Clos
    0.05
    /m
    0.04
    æİī
    0.04
    Activations Density 0.180%

    No Known Activations