© 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. 20576
    Prev
    Next
    INDEX
    Explanations

    whether

    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
    sar
    -0.07
    s
    -0.07
    erma
    -0.07
     faptul
    -0.07
    sik
    -0.07
    arren
    -0.07
    WND
    -0.07
    ersions
    -0.07
    sale
    -0.06
    ï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭ
    -0.06
    POSITIVE LOGITS
    hood
    0.07
    Ñİ
    0.06
    unya
    0.06
    ÑĬ
    0.06
    utter
    0.05
    ey
    0.05
    ly
    0.05
    iest
    0.05
    mente
    0.05
    åĬ¡
    0.05
    Activations Density 0.018%

    No Known Activations