© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22288
    Prev
    Next
    INDEX
    Explanations

    anything or any

    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
    fore
    -0.07
    ä¿Ŀè¯ģåħ¶
    -0.06
    çĶ±åħ¶
    -0.06
    orious
    -0.06
    üten
    -0.06
     ÙħØŃاÙģظ
    -0.06
    ä¸¥æł¼è¦ģæ±Ĥ
    -0.06
    æŶåĢĻ
    -0.06
    人æĿ¥è¯´
    -0.06
    çŃīçī¹æ®Ĭ
    -0.06
    POSITIVE LOGITS
    ÙĬØ·
    0.06
    abee
    0.06
    geist
    0.05
    طا
    0.05
     Anything
    0.05
    æĢĢçĸij
    0.05
    idget
    0.05
    arana
    0.05
    ÙĪسة
    0.05
    æĬĬ
    0.05
    Activations Density 0.032%

    No Known Activations