© 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. 20604
    Prev
    Next
    INDEX
    Explanations

    if they

    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
    omm
    -0.07
    EAR
    -0.07
    æºĸ
    -0.07
    éric
    -0.06
    úa
    -0.06
    کار
    -0.06
    好åĥıæĺ¯
    -0.06
    ØŃÙĪ
    -0.06
    elden
    -0.06
    ooth
    -0.06
    POSITIVE LOGITS
    lerce
    0.05
    jos
    0.04
    by
    0.04
    unlikely
    0.04
    ç³»åĪĹ
    0.04
    IBM
    0.04
     تÙĪسط
    0.04
     +
    0.04
    æĪĴ
    0.04
     IBM
    0.04
    Activations Density 0.005%

    No Known Activations