© 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. 17349
    Prev
    Next
    INDEX
    Explanations

    latex document structure

    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
     lẫn
    -0.07
    mith
    -0.07
    ÙħاÙĦ
    -0.06
    aturahmi
    -0.06
    лÑİ
    -0.06
    viso
    -0.06
    kring
    -0.06
    ì²´ê³Ħ
    -0.06
    amak
    -0.06
    alement
    -0.06
    POSITIVE LOGITS
    acon
    0.06
    olas
    0.05
    èĻ½çĦ¶æľī
    0.05
    空çļĦ
    0.05
    æį®
    0.05
    Ķ
    0.05
    buah
    0.05
     explain
    0.05
     ####
    0.05
    ritis
    0.05
    Activations Density 0.003%

    No Known Activations