© 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. 21464
    Prev
    Next
    INDEX
    Explanations

    also followed by specific words

    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
    缸åħ³ä¿¡æģ¯
    -0.06
    åħ·æľī以ä¸ĭ
    -0.06
    ä»»ä½ķéĹ®é¢ĺ
    -0.05
    ÅĽc
    -0.05
    uhu
    -0.05
     overtime
    -0.05
    تÙĩ
    -0.05
    æĢ¥äºİ
    -0.05
    alli
    -0.05
    ngo
    -0.05
    POSITIVE LOGITS
    sters
    0.06
    å°½éĩı
    0.06
    ÙĬد
    0.05
    é¢Ŀ
    0.05
    ing
    0.05
    ster
    0.05
     Pud
    0.05
    olling
    0.05
    itud
    0.05
    稳
    0.05
    Activations Density 0.005%

    No Known Activations