© 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. 19193
    Prev
    Next
    INDEX
    Explanations

    understand

    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
    æ£ł
    -0.06
    ecd
    -0.06
    adb
    -0.06
    engel
    -0.06
    Unchecked
    -0.06
     THERE
    -0.06
    ebut
    -0.06
    мееÑĤÑģÑı
    -0.06
     Ideal
    -0.06
     imperfect
    -0.06
    POSITIVE LOGITS
     japon
    0.05
    临éŨ
    0.05
     portion
    0.05
    被åŃIJ
    0.05
    éĥ¨åĪĨ
    0.05
    å®ĺ
    0.05
    æ¦Ĥ念
    0.05
     distinguished
    0.05
    åIJĽå®ī
    0.05
     guaranteed
    0.05
    Activations Density 0.264%

    No Known Activations