© 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. 20920
    Prev
    Next
    INDEX
    Explanations

    opportunity to do something

    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
    æĪijåıijçİ°
    -0.06
    åıijçİ°
    -0.06
    è®°å¾Ĺ
    -0.06
    estelle
    -0.06
     notably
    -0.06
    åıijçİ°æľī
    -0.06
    åıijçİ°çļĦ
    -0.06
    èħ¾
    -0.05
     features
    -0.05
    acing
    -0.05
    POSITIVE LOGITS
    atron
    0.06
    èĢģèĢħ
    0.06
    enn
    0.05
    å¥īä¸Ĭ
    0.05
    çļĦ交æµģ
    0.05
    åį±éĻ©æĢ§
    0.05
    YC
    0.05
    iro
    0.05
    unix
    0.05
    ιÏī
    0.05
    Activations Density 0.005%

    No Known Activations