© 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. 19822
    Prev
    Next
    INDEX
    Explanations

    either/or choices

    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
    irma
    -0.06
     true
    -0.05
    çŃ
    -0.05
    è¦ģæĪij
    -0.05
     fundamental
    -0.05
    пол
    -0.05
    åħ¶å®ŀæĺ¯
    -0.05
    ibat
    -0.05
    éħĶ
    -0.05
    n
    -0.05
    POSITIVE LOGITS
    åıĪä¸įèĥ½
    0.09
     neither
    0.08
    Either
    0.07
    reau
    0.07
    åıĪä¸į
    0.07
    ä¹Łä¸įèĥ½
    0.07
    asca
    0.07
    æĽ´ä¸įèĥ½
    0.06
     either
    0.06
     EITHER
    0.06
    Activations Density 0.337%

    No Known Activations