© 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. 22584
    Prev
    Next
    INDEX
    Explanations

    strudel and sweet onions

    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
    еÑĪ
    -0.06
    iri
    -0.05
    ä¸ĢåĪĨ
    -0.05
     reins
    -0.05
     Ñĥл
    -0.05
    ersten
    -0.05
    enor
    -0.05
    unter
    -0.05
     overrun
    -0.05
    çĽ¸äº²
    -0.05
    POSITIVE LOGITS
    åĮºéķ¿
    0.06
     thâm
    0.05
    .Hosting
    0.05
    ä½ľä¸ºä¸Ģç§į
    0.05
    endoza
    0.05
     Anonymous
    0.05
     pig
    0.05
    rawing
    0.05
    åĪĨæŀIJæ³ķ
    0.05
    æľ¬æĺ¯
    0.05
    Activations Density 0.004%

    No Known Activations