© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18208
    Prev
    Next
    INDEX
    Explanations

    friendly

    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
    end
    -0.06
    Ø«
    -0.05
    Uploaded
    -0.05
    æį¢ä¸Ģ个
    -0.05
    éĵħ
    -0.05
    ¥
    -0.05
    彩
    -0.05
    çIJĨåѦ
    -0.05
    åĴĮä¸ī
    -0.05
    å½¢èī²
    -0.05
    POSITIVE LOGITS
     everywhere
    0.06
    å¤ļçĶ¨
    0.05
    横è¡Į
    0.05
    ertz
    0.05
    éģįåľ°
    0.05
    éľĢè¦ģçĶ¨
    0.05
    èĮĥåĽ´åĨħ使çĶ¨
    0.05
    ä¼ļè§īå¾Ĺ
    0.05
    keur
    0.05
    erguson
    0.05
    Activations Density 0.021%

    No Known Activations