© 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. 22430
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    enda
    -0.06
    atan
    -0.05
    å½Ĵ
    -0.05
    æ²®
    -0.05
    欺
    -0.05
    acio
    -0.05
    ä¸į幸
    -0.05
     daños
    -0.05
    éĻĦåĽ¾
    -0.05
    çķĻåŃĺ
    -0.05
    POSITIVE LOGITS
    Prix
    0.06
    ÑģÑĬ
    0.06
    éfono
    0.06
    raith
    0.06
    eref
    0.06
    prix
    0.06
    æĤīå°¼
    0.06
    kurat
    0.05
    raison
    0.05
    aison
    0.05
    Activations Density 0.001%

    No Known Activations