© 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. 20059
    Prev
    Next
    INDEX
    Explanations

    code tag completions

    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
    odon
    -0.07
    (es
    -0.06
    rush
    -0.06
    ächs
    -0.06
    ç®Ĺä»Ģä¹Ī
    -0.06
    пÑĥÑģк
    -0.06
    res
    -0.06
     ÅĻ
    -0.06
    apas
    -0.06
    że
    -0.06
    POSITIVE LOGITS
    o
    0.06
    æ¯ĭ
    0.06
    æ´ĭ
    0.06
    atical
    0.05
    ebilecek
    0.05
    ogram
    0.05
    ìĭ¬
    0.05
    å·¥åķĨ
    0.05
    åIJģ
    0.05
    ีà¹īยว
    0.05
    Activations Density 0.001%

    No Known Activations