© 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. 21425
    Prev
    Next
    INDEX
    Explanations

    beginning with

    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
    êne
    -0.06
    åľ¨æĹ¥å¸¸
    -0.06
    allas
    -0.06
    ômes
    -0.06
    æĹ¥å¸¸
    -0.06
    åľ¨æĹ¥å¸¸çĶŁæ´»ä¸Ń
    -0.06
     Guarda
    -0.06
    nhof
    -0.06
    ipay
    -0.06
    æĹ¥å¸¸çļĦ
    -0.06
    POSITIVE LOGITS
     excluding
    0.05
    å®ľ
    0.05
    L
    0.05
    perl
    0.05
     organ
    0.05
    éĻ¤
    0.05
     aside
    0.05
     spanning
    0.05
    修订
    0.05
    ä¸įè¿ľ
    0.05
    Activations Density 0.004%

    No Known Activations