© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18149
    Prev
    Next
    INDEX
    Explanations

    maturity, olds, view, purchasing

    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
    /latest
    -0.06
    (rawValue
    -0.06
    ucker
    -0.06
    .raise
    -0.06
    ä¾Ŀæ³ķé¡»ç»ı
    -0.06
    注éĩį
    -0.06
    ?”.
    -0.05
    Fabr
    -0.05
    ayakan
    -0.05
    InSection
    -0.05
    POSITIVE LOGITS
    žite
    0.06
    çļĦåŃIJ
    0.05
    oze
    0.05
    áv
    0.05
    еÑĩа
    0.05
    çļĦæŃ£ç¡®
    0.05
    Į
    0.05
    çļĦåıį
    0.05
    doch
    0.05
    ceptor
    0.05
    Activations Density 0.001%

    No Known Activations