© 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. 21169
    Prev
    Next
    INDEX
    Explanations

    what is this?

    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
     nadr
    -0.06
    èĩªçĦ¶
    -0.06
    uits
    -0.06
    ikat
    -0.06
    åĹ£
    -0.05
    å·¡åĽŀ
    -0.05
    ayaan
    -0.05
    णि
    -0.05
    é³į
    -0.05
    deutsch
    -0.05
    POSITIVE LOGITS
    press
    0.06
    eens
    0.06
     اÙĨÚ¯
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
    rf
    0.05
    Ñīо
    0.05
    Ú©Ùĩ
    0.05
    pasar
    0.05
    æŶåĢĻ
    0.05
    =db
    0.05
    Activations Density 0.014%

    No Known Activations