© 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. 21925
    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
    اÙĨÙĩ
    -0.06
    requ
    -0.06
    Æ¡
    -0.06
    othi
    -0.06
    å°Ķ夫
    -0.06
    ç¦
    -0.06
    elper
    -0.05
    à¹ģà¸Ľ
    -0.05
     gar
    -0.05
     compr
    -0.05
    POSITIVE LOGITS
    åĩºä¸į
    0.06
    urgia
    0.05
     conditional
    0.05
     just
    0.05
     Notice
    0.05
    ÅĽcie
    0.05
    ulos
    0.05
     Homme
    0.05
     disp
    0.05
     become
    0.05
    Activations Density 0.000%

    No Known Activations