© 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. 18481
    Prev
    Next
    INDEX
    Explanations

    cherries, Chin, Answer

    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
    ingt
    -0.06
    agment
    -0.06
    ernet
    -0.06
    öch
    -0.06
    ertype
    -0.06
    öö
    -0.06
    ç
    -0.05
    翱
    -0.05
    agli
    -0.05
    istry
    -0.05
    POSITIVE LOGITS
    æĻĸ
    0.06
    éĵģçļ®
    0.06
    éľĢçĶ¨
    0.06
    浪
    0.06
    ally
    0.05
    iju
    0.05
     dime
    0.05
    èĤļåŃIJéĩĮ
    0.05
    ija
    0.05
    qu
    0.05
    Activations Density 0.053%

    No Known Activations