© 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. 18838
    Prev
    Next
    INDEX
    Explanations

    Python package structure and documentation

    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
    antro
    -0.06
    ганÑĤ
    -0.06
    frist
    -0.06
    ÙĨاÙĪÙĦ
    -0.06
    ething
    -0.06
    reso
    -0.06
    apur
    -0.06
    etr
    -0.06
    é«ĺä¸Ģ
    -0.06
    kezés
    -0.06
    POSITIVE LOGITS
    èĵ
    0.05
    æĶ¶
    0.05
    缺æįŁ
    0.05
    éĩĩæĶ¶
    0.05
    (abs
    0.05
    éĻ
    0.04
    icom
    0.04
    éĤ£åľº
    0.04
    缺货
    0.04
     quel
    0.04
    Activations Density 0.003%

    No Known Activations