© 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. 20528
    Prev
    Next
    INDEX
    Explanations

    framed doorway

    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
    oner
    -0.07
    prób
    -0.07
    æľ¨é½IJ
    -0.07
     Unidos
    -0.07
    anker
    -0.07
    онеÑĢ
    -0.06
    ÑĢÑİ
    -0.06
     Junction
    -0.06
    ubber
    -0.06
    arang
    -0.06
    POSITIVE LOGITS
    ep
    0.05
    ...
    0.05
     sh
    0.05
    uer
    0.05
    esh
    0.04
    gu
    0.04
     prospects
    0.04
     Sh
    0.04
    sh
    0.04
    halb
    0.04
    Activations Density 0.001%

    No Known Activations