© 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. 17901
    Prev
    Next
    INDEX
    Explanations

    Professor of

    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
     individual
    -0.06
    æĥ³åĩº
    -0.06
     Individ
    -0.05
    ä¸įæľį
    -0.05
    tol
    -0.05
    ollect
    -0.05
    äºİäºĭ
    -0.05
    ze
    -0.05
    åħ¨åĽ½
    -0.05
     ga
    -0.05
    POSITIVE LOGITS
    çī¹èģĺ
    0.07
    ueb
    0.06
    رÙĪب
    0.06
    oeuvre
    0.06
    stoffen
    0.06
    æĺłå°Ħ
    0.06
    Pred
    0.06
    annon
    0.06
     Malam
    0.06
    åķ¡
    0.06
    Activations Density 0.110%

    No Known Activations