© 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. 20666
    Prev
    Next
    INDEX
    Explanations

    Recognizing related concepts

    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
     compromet
    -0.06
    éĤ£äºĽå¹´
    -0.06
     близко
    -0.05
    å§Ĩ
    -0.05
     privilegi
    -0.05
    æķ´ä¸ªéĹ®é¢ĺ
    -0.05
     amator
    -0.05
     beur
    -0.05
    ovie
    -0.05
    åħ³éĶ®çݯèĬĤ
    -0.05
    POSITIVE LOGITS
    以大
    0.06
    xi
    0.06
    è·»
    0.05
     Domino
    0.05
    åĴĮ红
    0.05
    ucumber
    0.05
     Sinai
    0.05
    hap
    0.05
    以åįĹ
    0.05
    XL
    0.05
    Activations Density 0.008%

    No Known Activations