© 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. 20131
    Prev
    Next
    INDEX
    Explanations

    past tense and descriptive states

    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
     repeatedly
    -0.05
    peated
    -0.05
     regardless
    -0.05
    amis
    -0.05
    ä¿ĥ
    -0.05
     during
    -0.05
    zas
    -0.05
    æ³ī
    -0.05
    æ£Ģ
    -0.05
    ä¹ĭåIJİ
    -0.05
    POSITIVE LOGITS
    ÑģÑĤик
    0.07
    epend
    0.06
    æĬijæĪĸ
    0.06
    intos
    0.06
    wic
    0.06
    ä¸Ģèĩ´è®¤ä¸º
    0.06
    åıĹåĪ¶
    0.06
    ç´§å¯ĨèģĶç³»
    0.06
    haus
    0.06
    funk
    0.06
    Activations Density 0.018%

    No Known Activations