© 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. 18390
    Prev
    Next
    INDEX
    Explanations

    .com skiing syndrome April

    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
    iglio
    -0.07
    ãĤ¹ãĥĿ
    -0.07
    autant
    -0.07
    اÙģÙĬ
    -0.06
    iming
    -0.06
    çĦ¡ãģĹ
    -0.06
     dettaglio
    -0.06
    acking
    -0.06
    ÛĮÚ©ÙĨ
    -0.06
    acon
    -0.06
    POSITIVE LOGITS
    emon
    0.05
    éĴĪ对
    0.05
    ä¸įè¦ģåľ¨
    0.05
    çĻ»
    0.04
    æĸ°æĹ¶æľŁ
    0.04
    串è¡Į
    0.04
     tun
    0.04
    ook
    0.04
    ::-
    0.04
    åĤ¨å¤ĩ
    0.04
    Activations Density 0.002%

    No Known Activations