© 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. 19384
    Prev
    Next
    INDEX
    Explanations

    manifest package

    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
    è¿Ļä¹Ī好
    -0.06
    ility
    -0.06
    ired
    -0.06
    éĤ£ä¹Ī好
    -0.06
     such
    -0.05
    ourced
    -0.05
    ç»ı审çIJĨæŁ¥æĺİ
    -0.05
    fulness
    -0.05
    lox
    -0.05
    afil
    -0.05
    POSITIVE LOGITS
     оÑģвобо
    0.06
    ecco
    0.05
    itu
    0.05
    osten
    0.05
     masturb
    0.05
    åĩłå®¶
    0.05
    ä½ľåĵģçļĦ
    0.05
    guardo
    0.05
    ürlich
    0.05
    åıĺåĬ¨
    0.05
    Activations Density 0.001%

    No Known Activations