© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19620
    Prev
    Next
    INDEX
    Explanations

    belong

    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
     пÑĢоÑĦ
    -0.07
     seterusnya
    -0.06
    èĤļ
    -0.06
    èħ°
    -0.06
     meÄij
    -0.06
    isht
    -0.06
     ciertos
    -0.06
    硬
    -0.05
    umpt
    -0.05
    /cgi
    -0.05
    POSITIVE LOGITS
     envis
    0.06
    ä¼Łä¸ļ
    0.06
    éĻĦ带
    0.05
    Histoire
    0.05
    urre
    0.05
     airst
    0.05
     a
    0.05
     meant
    0.05
    -Al
    0.05
    为顾客
    0.05
    Activations Density 0.001%

    No Known Activations