© 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. 21596
    Prev
    Next
    INDEX
    Explanations

    code snippets or technical text

    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
    othi
    -0.05
    vers
    -0.05
    lán
    -0.05
    “
    -0.05
    olato
    -0.05
    ãģĦãģ¡
    -0.05
    ’(
    -0.05
    çļĦä¸Ģ声
    -0.05
    colo
    -0.05
    “(
    -0.05
    POSITIVE LOGITS
    ä¸įè¡°
    0.06
    æľºçĶµä¸Ģä½ĵåĮĸ
    0.06
    /MIT
    0.06
    çĶµèĦijçīĪ
    0.05
    ð
    0.05
    ikt
    0.05
    ãĥıãĥ¼ãĥī
    0.05
     diras
    0.05
     Hopkins
    0.05
    ä¼IJ
    0.05
    Activations Density 0.003%

    No Known Activations