© 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. 20426
    Prev
    Next
    INDEX
    Explanations

    opt

    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
    ض
    -0.07
    ÙĪار
    -0.05
    èĤļ
    -0.05
    s
    -0.05
    efs
    -0.05
    ä¿Ŀè¯ģ
    -0.05
    lie
    -0.05
    configure
    -0.05
     Ùħض
    -0.05
    axes
    -0.05
    POSITIVE LOGITS
     ÑĦакÑĤ
    0.06
    ovac
    0.06
    apt
    0.06
    chal
    0.06
    ä¸īåħĥ
    0.06
    ÑĢÑıн
    0.06
    åħ·æľī以ä¸ĭ
    0.06
    ä¸įåħ¥
    0.06
    è¯Ń
    0.06
    æľī以ä¸ĭ
    0.06
    Activations Density 0.003%

    No Known Activations