© 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. 21777
    Prev
    Next
    INDEX
    Explanations

    familial relationships

    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
    æľīçļĦ
    -0.06
    rophe
    -0.06
     carn
    -0.05
    ilh
    -0.05
    дейÑģÑĤвиÑı
    -0.05
    
    -0.05
    Ú¯ÛĮ
    -0.05
     ì§Ģ
    -0.05
    mill
    -0.05
    æľīä½į
    -0.05
    POSITIVE LOGITS
    缸
    0.06
    umeur
    0.06
    ارد
    0.05
     unavoid
    0.05
    arence
    0.05
     necess
    0.05
    宾
    0.05
    &E
    0.05
    attro
    0.05
     observation
    0.05
    Activations Density 0.015%

    No Known Activations