© 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. 21553
    Prev
    Next
    INDEX
    Explanations

    and punctuation

    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
    اÙĩ
    -0.07
    åIJĦè¡Į
    -0.06
    ä¸īéĢļ
    -0.06
    onné
    -0.06
    ience
    -0.05
    çĶ±åIJĦ
    -0.05
    åĨ·æ±Ĺ
    -0.05
    je
    -0.05
    rosso
    -0.05
    tees
    -0.05
    POSITIVE LOGITS
    é«ĵ
    0.06
    کارÛĮ
    0.06
    åħ¬è®¤
    0.06
    CAN
    0.06
    并åıĸå¾Ĺ
    0.05
     ÑĤаки
    0.05
    æĺ¯ä¸Ģ缴
    0.05
     chyba
    0.05
    quot
    0.05
     hinweg
    0.05
    Activations Density 0.005%

    No Known Activations