© 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. 17525
    Prev
    Next
    INDEX
    Explanations

    company announcements today

    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
    ei
    -0.06
    æĺİæĺ¾æĶ¹åĸĦ
    -0.05
    Thin
    -0.05
    ä¸Ģéĸĭå§ĭ
    -0.05
     initially
    -0.05
    Ħ
    -0.05
     perek
    -0.05
     ensure
    -0.05
    æĺĮ
    -0.05
     ens
    -0.05
    POSITIVE LOGITS
    quires
    0.06
    ê±°
    0.06
    ometrics
    0.06
    à¸ķุ
    0.06
    è°ĥ
    0.06
    olith
    0.06
    æĸ¥
    0.06
    że
    0.06
    ÑĢоли
    0.05
    ROL
    0.05
    Activations Density 0.300%

    No Known Activations