© 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. 21375
    Prev
    Next
    INDEX
    Explanations

    number of

    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
    erima
    -0.07
    ely
    -0.06
    ÙĬÙĨØ©
    -0.06
    legates
    -0.06
    nö
    -0.06
     mili
    -0.06
    erate
    -0.06
     ingle
    -0.06
    rightness
    -0.05
    mals
    -0.05
    POSITIVE LOGITS
    æĪij羣
    0.06
    agine
    0.05
    chim
    0.05
    Òĵ
    0.05
    ä¸ºå®ľ
    0.05
    è¿Ļæł·ä¸Ģ个
    0.05
    anh
    0.05
    onym
    0.05
     Chim
    0.05
     vrais
    0.05
    Activations Density 0.027%

    No Known Activations