© 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. 17332
    Prev
    Next
    INDEX
    Explanations

    **continuous differentiable function**

    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
    ster
    -0.07
    vir
    -0.06
     ÐĴÑĩеÑĢа
    -0.05
     raid
    -0.05
     relationships
    -0.05
    ever
    -0.05
     yönelik
    -0.05
    ardless
    -0.05
    hardt
    -0.05
    ä¸įæĶ¾
    -0.05
    POSITIVE LOGITS
     continuity
    0.07
    intégr
    0.06
    éģľ
    0.06
    åĮĸçī©
    0.06
    åĨ³èĥľ
    0.06
    åħīæ»ij
    0.06
    è¿ŀç»ŃæĢ§
    0.06
    éĹ´æĸŃ
    0.06
    çijķ
    0.06
    éĢĬ
    0.06
    Activations Density 0.072%

    No Known Activations