© 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. 17431
    Prev
    Next
    INDEX
    Explanations

    comma separated

    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
    çĴŀ
    -0.06
    æķĻåħ»
    -0.06
     sens
    -0.06
    ä½IJ
    -0.05
    æľĿ
    -0.05
    ardu
    -0.05
    èµĦæľ¬
    -0.05
    æĿ°
    -0.05
    èµĦæºIJ
    -0.05
    ens
    -0.05
    POSITIVE LOGITS
    æĿĥçļĦ
    0.06
    æŀĹä¸Ń
    0.06
    é¡ĺ
    0.06
    otan
    0.05
    åĵį
    0.05
    nÃŃm
    0.05
    å¿ĺä¸įäºĨ
    0.05
    æĬĦæĬ¥
    0.05
    æµģçļĦ
    0.05
    laget
    0.05
    Activations Density 0.003%

    No Known Activations