© 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. 19345
    Prev
    Next
    INDEX
    Explanations

    faintness, dizziness, syncope, vertigo

    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
    åĬ¨åijĺ
    -0.07
    áĥ©
    -0.06
    ä¸Ĭè¿°ä½ľåĵģ
    -0.06
    enix
    -0.06
    æŶæĬ¥
    -0.06
    .rectangle
    -0.06
    åĩºåĬĽ
    -0.06
     ÑĤÑĢанÑģпоÑĢ
    -0.06
    enko
    -0.06
     dikar
    -0.06
    POSITIVE LOGITS
    quiv
    0.06
    sets
    0.06
    acol
    0.05
    OrNull
    0.05
    inha
    0.05
    uge
    0.05
    pon
    0.05
    afi
    0.05
    izzy
    0.05
    oucher
    0.05
    Activations Density 0.005%

    No Known Activations