© 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. 17143
    Prev
    Next
    INDEX
    Explanations

    numbers followed by specific words

    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
    itul
    -0.06
    ä¸īéĥ¨åĪĨ
    -0.06
    è¿Ļä¸īç§į
    -0.06
    ä¸ī款
    -0.06
    ä¸īç§į
    -0.06
    è¶ģ
    -0.06
    ãĢģ
    -0.06
    è¿Ļä¸ī
    -0.05
     three
    -0.05
    _,
    -0.05
    POSITIVE LOGITS
    omatik
    0.06
    zionali
    0.06
    asso
    0.06
    bable
    0.06
    è¾ĥå°ıçļĦ
    0.06
    纳æĸ¯
    0.06
    åıĮè¾¹
    0.06
    åIJĦè¡Į
    0.06
    osal
    0.06
    orer
    0.05
    Activations Density 0.014%

    No Known Activations