© 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. 22293
    Prev
    Next
    INDEX
    Explanations

    women's

    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
    Not in Any Lists

    No Comments

    Negative Logits
    orto
    -0.07
    iterr
    -0.07
    eprom
    -0.06
    esp
    -0.06
    igest
    -0.06
    izacion
    -0.06
    åŃ£çļĦ
    -0.06
    endada
    -0.06
    ontage
    -0.06
    bout
    -0.06
    POSITIVE LOGITS
    ç¦ģæŃ¢
    0.06
     no
    0.05
    éĹ´
    0.05
    “
    0.05
    aber
    0.05
    igin
    0.05
    æīĢåľ¨
    0.05
    ords
    0.05
     join
    0.05
    1
    0.05
    Activations Density 0.024%

    No Known Activations