© 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. 21506
    Prev
    Next
    INDEX
    Explanations

    actions and events

    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
    reds
    -0.06
    prs
    -0.06
    ragen
    -0.06
    бÑĢан
    -0.06
    åĴĮè¡ĮåĬ¨
    -0.06
    æĸ°ä¸ĸçķĮ
    -0.06
    roje
    -0.06
    äºİ人
    -0.06
    Å¡n
    -0.06
    uated
    -0.06
    POSITIVE LOGITS
    触
    0.06
    åįłåħ¬åı¸
    0.06
    éľ²
    0.05
    /dc
    0.05
    ie
    0.05
    ui
    0.05
    åıĹçļĦ
    0.05
    ulta
    0.05
    æĤ£
    0.05
    åıĹ
    0.05
    Activations Density 0.335%

    No Known Activations