© 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. 20287
    Prev
    Next
    INDEX
    Explanations

    numbered items in lists

    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
    éĥ¨ç½²
    -0.05
    åĪĨæ°´
    -0.05
    UX
    -0.05
    åŁİå¸Ĥ群
    -0.05
    odel
    -0.05
     seg
    -0.05
    åĴĮèĶ¬èıľ
    -0.05
    üter
    -0.04
    ìħĺ
    -0.04
    reiten
    -0.04
    POSITIVE LOGITS
    ly
    0.06
    æĺı
    0.06
    zyn
    0.06
     APA
    0.06
    brio
    0.06
    为èį£
    0.06
    agnes
    0.06
    ¥
    0.06
     readOnly
    0.05
    clin
    0.05
    Activations Density 0.005%

    No Known Activations