© 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. 21795
    Prev
    Next
    INDEX
    Explanations

    diet or diets

    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
    åīĶ
    -0.06
    åĶ¯ä¸Ģä¸Ģ家
    -0.06
    abora
    -0.06
    incu
    -0.06
    ØŃÙĬÙĦ
    -0.05
    ,DB
    -0.05
    ificazione
    -0.05
    ámos
    -0.05
    otics
    -0.05
    éĻ¸
    -0.05
    POSITIVE LOGITS
    认为æĺ¯
    0.06
    جر
    0.05
    ØŃدÙī
    0.05
    å¼ķçĶ¨çļĦ
    0.05
    kur
    0.05
    Tw
    0.05
     bah
    0.05
    æŃ¤ä¸º
    0.05
    alcon
    0.05
    erson
    0.05
    Activations Density 0.014%

    No Known Activations