© 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. 18565
    Prev
    Next
    INDEX
    Explanations

    philosophical or existential questions

    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
    足
    -0.05
    ane
    -0.05
     (
    -0.04
    ä»İæĶ¿
    -0.04
    hi
    -0.04
    izedName
    -0.04
    ên
    -0.04
    å·«
    -0.04
    شرة
    -0.04
     nas
    -0.04
    POSITIVE LOGITS
    uria
    0.06
    dsl
    0.06
     ÑģовмеÑģÑĤи
    0.06
    $l
    0.06
    plier
    0.06
    kaar
    0.06
    önen
    0.06
     ÑĤÑĢанÑģп
    0.06
    æŀĦçŃijçī©
    0.06
    /Area
    0.06
    Activations Density 0.014%

    No Known Activations