© 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. 20316
    Prev
    Next
    INDEX
    Explanations

    and then

    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
    ãģ¿ãĤĦ
    -0.07
    éģĩè§ģ
    -0.06
    å¤ļäºĨ
    -0.06
    []}
    -0.06
    ãģªãģĹ
    -0.06
    ×Ĺ×ķת
    -0.06
    cieli
    -0.06
     جذاب
    -0.06
    åķĨåŁİ
    -0.05
    ÑĤли
    -0.05
    POSITIVE LOGITS
    wish
    0.06
    æĸ¹åIJijçļĦ
    0.05
    anga
    0.05
    ixer
    0.05
    atches
    0.05
    erver
    0.05
    éĩİ
    0.05
    coord
    0.05
    ously
    0.05
    æĦıè¯Ĩåľ°
    0.05
    Activations Density 0.001%

    No Known Activations