© 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. 22442
    Prev
    Next
    INDEX
    Explanations

    especially + adjective/verb

    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
     Wouldn
    -0.06
    opportun
    -0.06
    istics
    -0.06
    onsense
    -0.06
    ecil
    -0.06
    è®°èĢħäºĨ解åĪ°
    -0.06
    ettle
    -0.05
    èªĮ
    -0.05
    ynthia
    -0.05
    à¸ĸึà¸ĩ
    -0.05
    POSITIVE LOGITS
    en
    0.09
    es
    0.08
    y
    0.08
    asinya
    0.07
    al
    0.07
    Ùĩ
    0.07
    ioned
    0.07
    à¹Į
    0.07
    schnitt
    0.07
    ed
    0.07
    Activations Density 0.012%

    No Known Activations