© 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. 22388
    Prev
    Next
    INDEX
    Explanations

    replace with

    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
    æķ´
    -0.07
    åĢį
    -0.06
    å·¥ä½ľ
    -0.06
     ìĶ
    -0.05
    TM
    -0.05
    ech
    -0.05
     пÑĢопа
    -0.05
    ÑģаÑĢ
    -0.05
    å¤§æ±Ł
    -0.05
    å¾Īå¤ļ
    -0.05
    POSITIVE LOGITS
    -Trump
    0.07
    å¦Ĥåıijçİ°
    0.07
    ä»»ä½ķéĹ®é¢ĺ
    0.06
    ness
    0.06
    iese
    0.06
    dej
    0.06
    лове
    0.06
    åĪĨ许
    0.06
    ignor
    0.06
    ÐķÐłÐķ
    0.06
    Activations Density 0.001%

    No Known Activations