© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18663
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tawa
    -0.08
    elai
    -0.07
    quinas
    -0.07
    веÑĢÑĪенÑģÑĤво
    -0.07
    rox
    -0.07
    WithTitle
    -0.07
     Fábio
    -0.07
    ียรà¹Į
    -0.07
    sene
    -0.07
    ä¸ĭæľŁ
    -0.07
    POSITIVE LOGITS
    |
    0.06
    -
    0.06
    1
    0.05
    кÑĢе
    0.05
    0.05
    j
    0.05
     vs
    0.05
    ia
    0.05
     can
    0.05
    {
    0.05
    Activations Density 0.000%

    No Known Activations