© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18707
    Prev
    Next
    INDEX
    Explanations

    new entities

    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
    èĢĮèµ·
    -0.08
    æķijçģ¾
    -0.07
    èµ·æĭį
    -0.06
    divide
    -0.06
    èĹ
    -0.06
    ربÛĮ
    -0.06
    çİ°åľ¨å¼Ģå§ĭ
    -0.06
    åĪĿæŃ¥
    -0.06
    åħ¼æĢ»ç»ıçIJĨ
    -0.06
     inicial
    -0.06
    POSITIVE LOGITS
    éģĵéģĵ
    0.06
    illes
    0.06
    ül
    0.06
    åħĮ
    0.05
    å°ı
    0.05
     Const
    0.05
    itic
    0.05
    常
    0.05
    æľĪçīĻ
    0.05
    ä¼´
    0.05
    Activations Density 0.045%

    No Known Activations