© 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. 21113
    Prev
    Next
    INDEX
    Explanations

    mechanism and intermediate formation

    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
    ä¸Ģ天
    -0.06
    ÃŃdu
    -0.06
     XXL
    -0.06
     assemb
    -0.06
    ÃŃfer
    -0.06
    صب
    -0.05
    ä¸ĢæĹ¥
    -0.05
    adeiras
    -0.05
    iversity
    -0.05
    æĺ¯ä¸Ģå¹´
    -0.05
    POSITIVE LOGITS
    æľºåĪ¶
    0.07
    åıijèµ·
    0.06
    çļĦå½¢æĪIJ
    0.06
    formation
    0.06
     mechanisms
    0.05
     mechanism
    0.05
    áºł
    0.05
    åĮĸ为
    0.05
    çļĦ解éĩĬ
    0.05
    ÑĨионно
    0.05
    Activations Density 0.107%

    No Known Activations