© 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. 16559
    Prev
    Next
    INDEX
    Explanations

    cell tumors /c

    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
    Negative Logits
    ergus
    -0.06
     encont
    -0.06
    oul
    -0.05
    kus
    -0.05
    è¿Ļä¹Īç®Ģåįķ
    -0.05
    urz
    -0.05
    몰
    -0.05
    kere
    -0.05
     and
    -0.05
    ìĿ´ëĿ¼ë©°
    -0.05
    POSITIVE LOGITS
    =/
    0.06
    å©·å©·
    0.06
    è°ĭåĪĴ
    0.06
    å®Į
    0.06
    SZ
    0.05
    airy
    0.05
     spoiler
    0.05
    ±
    0.05
    çĮ®
    0.05
     prom
    0.05
    Activations Density 0.390%

    No Known Activations