© 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. 20240
    Prev
    Next
    INDEX
    Explanations

    showing that he can

    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
    สัà¸į
    -0.06
    -last
    -0.06
     thang
    -0.06
     Operation
    -0.05
    actual
    -0.05
    ovan
    -0.05
    omot
    -0.05
    heil
    -0.05
    last
    -0.05
    éĢį
    -0.05
    POSITIVE LOGITS
    è´¹çŃī
    0.06
    åħ¬åı¸æıIJä¾Ľ
    0.06
    CAD
    0.06
    åħ¬åı¸çŃī
    0.06
    éĿĻçļĦ
    0.06
    нÑİ
    0.05
    hl
    0.05
    hesion
    0.05
    hab
    0.05
    ÑĢика
    0.05
    Activations Density 0.002%

    No Known Activations