© 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. 19399
    Prev
    Next
    INDEX
    Explanations

    features, descriptions, selling points

    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
    onet
    -0.07
     endanger
    -0.06
    å¿ħéľĢ
    -0.05
    æ´»åĬ¨åĴĮ
    -0.05
     harbor
    -0.05
    .setdefault
    -0.05
    æĺİç¡®è¦ģæ±Ĥ
    -0.05
     kind
    -0.05
    çļĦåŁºæľ¬è¦ģæ±Ĥ
    -0.05
    主è¦ģ人åijĺ
    -0.05
    POSITIVE LOGITS
    enia
    0.07
    åºĶæīĭ
    0.06
    fabs
    0.06
    žit
    0.06
    大ä¼ļä¸Ĭ
    0.05
    BRA
    0.05
    /release
    0.05
    amer
    0.05
    еÑģÑģ
    0.05
    Ñĩе
    0.05
    Activations Density 0.005%

    No Known Activations