© 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. 21281
    Prev
    Next
    INDEX
    Explanations

    book titles and authors

    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
    IVA
    -0.06
    -sdk
    -0.05
     Ridge
    -0.05
     asso
    -0.05
    çļĦè¯į
    -0.05
    gelegt
    -0.05
     carr
    -0.05
     opport
    -0.05
     Mellon
    -0.05
     конÑģо
    -0.05
    POSITIVE LOGITS
    _Dis
    0.06
    å¤Ń
    0.06
    ourd
    0.05
     ÑĦоÑĢÑĥ
    0.05
    åİĨåı²åĨĽäºĭ
    0.05
     outlining
    0.05
    fec
    0.05
    Bợi
    0.05
    latin
    0.05
    icer
    0.05
    Activations Density 0.003%

    No Known Activations