© 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. 19838
    Prev
    Next
    INDEX
    Explanations

    physical and abstract concepts

    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
    太çĻ½
    -0.06
    azzo
    -0.06
    nö
    -0.06
    hil
    -0.06
     favour
    -0.05
     favors
    -0.05
    borg
    -0.05
     favor
    -0.05
    زار
    -0.05
     unfavor
    -0.05
    POSITIVE LOGITS
    ä¸ĢæıIJ
    0.06
     ëĮĢíķľ
    0.06
    æĪĸ缺
    0.05
    åĽ¾çļĦ
    0.05
     Ñģпе
    0.05
    orb
    0.05
    æ¶Ī
    0.05
    ä¹ł
    0.05
    acam
    0.05
    åįĩ
    0.05
    Activations Density 0.032%

    No Known Activations