© 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. 20130
    Prev
    Next
    INDEX
    Explanations

    requires

    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
    meen
    -0.06
    ÑģÑĤÑĢе
    -0.06
    jal
    -0.06
    æŃ»äºº
    -0.06
    zeb
    -0.06
     SHR
    -0.06
    临éŨ
    -0.06
    غر
    -0.06
     McGr
    -0.06
    ÑĢиди
    -0.06
    POSITIVE LOGITS
    æī
    0.06
     ÐĹаÑĤо
    0.06
    æĬij
    0.05
    éģĵãģ®
    0.05
    ä¹ŀ
    0.05
    æĪIJåŀĭ
    0.05
    æij¸ç´¢
    0.05
    tap
    0.05
    ax
    0.05
    æĪIJæŀľ
    0.05
    Activations Density 0.024%

    No Known Activations