© 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. 22621
    Prev
    Next
    INDEX
    Explanations

    secondarily, double-blind

    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
     contradiction
    -0.05
    amme
    -0.05
    ean
    -0.05
     intros
    -0.05
    bane
    -0.05
    çĶ²çŃī
    -0.05
    羣æŃ£æĪIJ为
    -0.05
    ä¸Ļ
    -0.05
    èĤ¡æĮĩ
    -0.05
     confused
    -0.05
    POSITIVE LOGITS
    afür
    0.07
    çݲçıij
    0.06
    jour
    0.06
    _WIN
    0.06
    ighth
    0.06
     destro
    0.06
    åİĨåı²åĨĽäºĭ
    0.06
    åĮ»éĻ¢è¿Ľè¡Į
    0.06
    ermen
    0.05
     nev
    0.05
    Activations Density 0.001%

    No Known Activations