© 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. 21347
    Prev
    Next
    INDEX
    Explanations

    top followed by a number

    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
    modo
    -0.07
    -Russian
    -0.06
    agu
    -0.06
    gül
    -0.06
    äºİè¡Į
    -0.06
    å°±çŁ¥éģĵäºĨ
    -0.06
     ditar
    -0.06
    人士çļĦ
    -0.06
     ,'
    -0.06
    æĹłæįŁ
    -0.06
    POSITIVE LOGITS
    ings
    0.06
    å®
    0.06
    å¼ı
    0.06
    è°¬
    0.05
    æݨ
    0.05
    åĮĸçī©
    0.05
    åį¿
    0.05
    é¢IJ
    0.05
    iggs
    0.05
    åħ¶åIJİ
    0.05
    Activations Density 0.009%

    No Known Activations