© 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. 18343
    Prev
    Next
    INDEX
    Explanations

    St. Vincent, Washington, Jose, Esau

    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
    roid
    -0.07
     thereof
    -0.07
    lum
    -0.06
    æĺİçļĦ
    -0.06
    sten
    -0.06
    sta
    -0.06
     turno
    -0.06
     Chois
    -0.06
     cúp
    -0.06
    lus
    -0.06
    POSITIVE LOGITS
    ØŃÙĪ
    0.05
     circum
    0.05
     at
    0.05
     op
    0.05
    æĵį
    0.05
    å·¡
    0.05
     Saga
    0.05
    ãģªãģı
    0.05
     roots
    0.05
    åľºæĻ¯ä¸Ń
    0.05
    Activations Density 0.002%

    No Known Activations