© 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. 17904
    Prev
    Next
    INDEX
    Explanations

    drug suffixes ending in ol, ode, or, ix

    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
    empl
    -0.06
    ä¸įåľ¨
    -0.06
    éķ¿çĽ¸
    -0.06
    ÑĢемÑı
    -0.05
    -esque
    -0.05
    èĹĿ
    -0.05
    uality
    -0.05
    teil
    -0.05
    rient
    -0.05
    ariant
    -0.05
    POSITIVE LOGITS
    çĩĥæĶ¾
    0.06
    äºĮ度
    0.06
    NASA
    0.06
    лове
    0.06
    ØŃÙħد
    0.05
    mens
    0.05
    меннÑĭй
    0.05
    à¸Ńà¸ĩ
    0.05
    æľĪæ´»åĬ¨
    0.05
    ụt
    0.05
    Activations Density 0.030%

    No Known Activations