© 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. 20408
    Prev
    Next
    INDEX
    Explanations

    keywords, content, :

    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
    åĩłä¹İ
    -0.06
    ä¸ĢåŃĹ
    -0.06
     Rel
    -0.05
    Rel
    -0.05
    æ¹¾
    -0.05
    港
    -0.05
    еÑĩ
    -0.05
    æ··
    -0.05
    åħ³éĶ®è¯į
    -0.05
    æĪı
    -0.05
    POSITIVE LOGITS
     consigo
    0.06
    Ł
    0.06
    åĪ°åºķæĺ¯
    0.06
    å¾¹åºķ
    0.06
    解éĩĬéģĵ
    0.06
    究竣æĺ¯
    0.06
    yorum
    0.06
    icola
    0.06
    åİŁåĽłçļĦ
    0.06
     Butt
    0.06
    Activations Density 0.002%

    No Known Activations