© 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. 21811
    Prev
    Next
    INDEX
    Explanations

    have or has

    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
    czÄĻÅĽciej
    -0.08
    виÑģ
    -0.07
    éĿĻéĿĻ
    -0.06
    oyal
    -0.06
     Dise
    -0.06
    entras
    -0.06
    åį°
    -0.06
    çī¹åĪ«æĺ¯åľ¨
    -0.06
    lyn
    -0.06
     вÑĭÑħод
    -0.06
    POSITIVE LOGITS
    ä¸İåħ¶
    0.06
    èĪĩåħ¶
    0.05
    atically
    0.05
    æīĵäºĨ个
    0.05
     “
    0.05
    åıijå±ķä¸İ
    0.05
    åĴĮåħ¶
    0.05
    ÙĪØ´
    0.05
    pute
    0.05
    æĺ¯åħ¶
    0.05
    Activations Density 0.002%

    No Known Activations