© 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. 21085
    Prev
    Next
    INDEX
    Explanations

    layout orientation vertical column block

    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
    à¸Īี
    -0.06
    äºĨçļĦ
    -0.06
    ารà¸ĸ
    -0.06
     Zoll
    -0.06
    .PathVariable
    -0.06
    -0.06
    amil
    -0.05
    istri
    -0.05
    contre
    -0.05
    emberg
    -0.05
    POSITIVE LOGITS
    oric
    0.06
    cego
    0.06
    ARIO
    0.06
    yks
    0.06
    à¸Ńย
    0.06
    æ£Ģ
    0.05
    ÅĽwiÄĻ
    0.05
     vzn
    0.05
    ocking
    0.05
    å¤ĩ
    0.05
    Activations Density 0.002%

    No Known Activations