© 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. 17316
    Prev
    Next
    INDEX
    Explanations

    ={

    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
    ÑģÑĤÑĢо
    -0.07
    hir
    -0.07
    bane
    -0.06
    letal
    -0.06
    elsen
    -0.06
    avior
    -0.06
    çĤ¹å·¦åı³
    -0.06
     timur
    -0.06
    δικ
    -0.05
    ا
    -0.05
    POSITIVE LOGITS
    nya
    0.06
    åħ¸ç±į
    0.06
    igon
    0.06
    ä¸Ģæ»´
    0.05
     differential
    0.05
    elaide
    0.05
    æŃ£ç»ı
    0.05
    inent
    0.05
    illé
    0.05
     compre
    0.05
    Activations Density 0.004%

    No Known Activations