© 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. 19000
    Prev
    Next
    INDEX
    Explanations

    </TOKENS_AFTER_MAX_ACTIVATING_TOKEN><TOP_POSITIVE_LOGITS>finallyehnæľĢåIJİæĺ¯ë§Īì§Ģë§īìľ¼ë¡ľæĪIJæŀľè½¬åĮĸæľĢå¾Įãģ«completescrownedå½ĵçĦ¶è¦ģæµĵæµĵ</TOP_POSITIVE_LOGITS><TOP_ACTIVATING_TEXTS> an electromechanically operable

    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
    icle
    -0.05
    Ùħر
    -0.05
    ç¾¹
    -0.05
    ups
    -0.05
    iegel
    -0.05
    ander
    -0.05
    bo
    -0.05
    å¤ļéĥ¨
    -0.05
    enery
    -0.05
    Bo
    -0.05
    POSITIVE LOGITS
     finally
    0.07
    ehn
    0.06
    æľĢåIJİæĺ¯
    0.06
     ë§Īì§Ģë§īìľ¼ë¡ľ
    0.06
    æĪIJæŀľè½¬åĮĸ
    0.06
    æľĢå¾Įãģ«
    0.06
     completes
    0.06
     crowned
    0.06
    å½ĵçĦ¶è¦ģ
    0.06
    æµĵæµĵ
    0.06
    Activations Density 0.002%

    No Known Activations