© 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. 20941
    Prev
    Next
    INDEX
    Explanations

    where, when, which, wherein

    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
    Einst
    -0.06
    ½
    -0.06
    Cre
    -0.06
     Recently
    -0.05
     ↵	↵
    -0.05
    ãģĶ覧
    -0.05
    imana
    -0.05
    -wise
    -0.05
     recently
    -0.05
    ieran
    -0.05
    POSITIVE LOGITS
    ign
    0.06
    è¡Įä¹ĭ
    0.05
    IDL
    0.05
     hul
    0.05
    é£Ł
    0.05
     exits
    0.05
     concerned
    0.05
     exit
    0.05
    éĻĮ
    0.05
    edido
    0.05
    Activations Density 0.021%

    No Known Activations