© 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. 22490
    Prev
    Next
    INDEX
    Explanations

    How questions, syndromes, proper nouns

    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
    åIJŀ
    -0.05
    &
    -0.05
    pop
    -0.05
    rend
    -0.05
    è¿IJ
    -0.05
    h
    -0.05
    许
    -0.05
    rock
    -0.05
     Pop
    -0.04
    isd
    -0.04
    POSITIVE LOGITS
    Angeb
    0.07
    lez
    0.07
    ç¾İçijŀ
    0.07
    endszer
    0.07
    entric
    0.06
    çī¹èī²ç¾İé£Ł
    0.06
    arial
    0.06
    Ùģظ
    0.06
    биÑı
    0.06
    oule
    0.06
    Activations Density 0.001%

    No Known Activations