© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20864
    Prev
    Next
    INDEX
    Explanations

    minute

    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
    ziÄĻki
    -0.06
     пен
    -0.06
    presa
    -0.06
    rah
    -0.06
     fict
    -0.05
    .randrange
    -0.05
    à¸Ļาย
    -0.05
    intage
    -0.05
    letak
    -0.05
     СÑĤÑĢа
    -0.05
    POSITIVE LOGITS
    è¨Ģ
    0.06
    æĹłå°½çļĦ
    0.06
    avig
    0.05
    çİ°å®ŀçļĦ
    0.05
    AIT
    0.05
     ceci
    0.05
    oops
    0.05
    aur
    0.05
    æľ¬æĬ¥åijĬ
    0.05
    ense
    0.05
    Activations Density 0.004%

    No Known Activations