© 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. 17608
    Prev
    Next
    INDEX
    Explanations

    programming callback listeners

    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
    è¿İæİ¥
    -0.05
    çļĦ主导
    -0.05
    Âł
    -0.05
     perc
    -0.05
    ÅĤ
    -0.05
    atom
    -0.05
    avig
    -0.05
    exe
    -0.05
     ident
    -0.05
    rah
    -0.05
    POSITIVE LOGITS
    immers
    0.06
    "My
    0.06
     ÑĤем
    0.06
    ç½ķ
    0.06
    veje
    0.06
    è¾¹çķĮ
    0.06
    ukup
    0.06
    æĭ¼
    0.06
    lips
    0.06
    ردد
    0.06
    Activations Density 0.059%

    No Known Activations