© 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. 19782
    Prev
    Next
    INDEX
    Explanations

    bravereal thingchannel subsystemreset

    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
    æ¸ħ
    -0.05
    Data
    -0.05
    abh
    -0.05
    ún
    -0.05
    an
    -0.05
    opsis
    -0.05
    ello
    -0.05
     guest
    -0.05
    ÅĤow
    -0.04
     planen
    -0.04
    POSITIVE LOGITS
    diy
    0.07
     ferme
    0.07
    æ¶ī
    0.06
    ceg
    0.06
    пÑĥлÑĮ
    0.06
    ä¸Ģæĸ¹çļĦ
    0.06
     ine
    0.06
    ;z
    0.06
    ;y
    0.06
    SOLE
    0.06
    Activations Density 0.003%

    No Known Activations