© 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. 19375
    Prev
    Next
    INDEX
    Explanations

    new sentence or clause

    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
    rowned
    -0.07
    ConfigurationException
    -0.07
    fato
    -0.07
    éĩįè¦ģçļĦäºĭæĥħ
    -0.07
    esses
    -0.06
    åįĹåİ¿
    -0.06
    以åѦçĶŁ
    -0.06
    antik
    -0.06
    ./(
    -0.06
    éŨå°Ĩ
    -0.06
    POSITIVE LOGITS
    å®Ĺ
    0.05
    éĩİ
    0.05
    æĺĵ
    0.05
     Establish
    0.05
    c
    0.05
    å¾ħ
    0.05
    åĬĽ
    0.05
    éĢĤåºĶ
    0.05
    æīĢå¾Ĺ
    0.04
    ood
    0.04
    Activations Density 0.200%

    No Known Activations