© 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. 21903
    Prev
    Next
    INDEX
    Explanations

    killed, provided, underrated

    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
    åĪļ
    -0.07
    åĪļåĪļ
    -0.06
    åīĽ
    -0.06
    à¸ŀà¸Ńà¸Ķี
    -0.06
    纶
    -0.06
    èĤĩ
    -0.06
     CAO
    -0.05
    aac
    -0.05
    :&
    -0.05
    ién
    -0.05
    POSITIVE LOGITS
     ____
    0.07
     _____
    0.06
     ___
    0.06
     _
    0.06
     __
    0.06
     din
    0.06
    aud
    0.06
     ______
    0.06
    illed
    0.05
    alize
    0.05
    Activations Density 0.050%

    No Known Activations