© 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. 20196
    Prev
    Next
    INDEX
    Explanations

    state or relation following verbs

    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
    -record
    -0.06
    ÙĨع
    -0.05
    isar
    -0.05
    ĺ
    -0.05
     Bun
    -0.05
     ÏĢÏģÏī
    -0.05
    лко
    -0.05
    istring
    -0.05
    åIJİç»ı
    -0.05
    á»Ĺ
    -0.05
    POSITIVE LOGITS
    å¾ĹçĽĬ
    0.07
    åıijçĶŁåľ¨
    0.06
    οδο
    0.06
    ç²Ĺæļ´
    0.05
    minster
    0.05
     occurring
    0.05
    æĹłå¤Ħä¸įåľ¨
    0.05
    履约
    0.05
    åĢŁåĬĽ
    0.05
    è¶ĭ
    0.05
    Activations Density 0.010%

    No Known Activations