© 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. 16838
    Prev
    Next
    INDEX
    Explanations

    cannot / can't

    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
    UNG
    -0.06
     raw
    -0.05
    ä¸ĢæĿ¡é¾Ļ
    -0.05
     standby
    -0.05
    az
    -0.05
    aternion
    -0.05
    мееÑĤÑģÑı
    -0.05
    пеÑĤ
    -0.05
    -ready
    -0.05
    è¯Ľä»Ļ
    -0.05
    POSITIVE LOGITS
    icht
    0.06
    èIJ½åľ°
    0.06
     Tief
    0.06
    si
    0.05
    ogos
    0.05
    ugn
    0.05
    åħ®
    0.05
    arhus
    0.05
    ility
    0.05
    ç¥ŀçĪ¶
    0.05
    Activations Density 0.037%

    No Known Activations