© 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. 18470
    Prev
    Next
    INDEX
    Explanations

    closely

    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
     pháºŃn
    -0.07
    éħįç½®æĸ¹éĿ¢
    -0.06
    çĤ¹å°ı
    -0.06
    tric
    -0.06
    影迷
    -0.06
    inkan
    -0.05
    -most
    -0.05
     à¹Ģà¸Ľà¸Ńรà¹Įà¹Ģà¸ĭà¹ĩà¸Ļà¸ķà¹Į
    -0.05
     portefeuille
    -0.05
    меÑĤим
    -0.05
    POSITIVE LOGITS
    ä¸įåı¯æĢĿè®®
    0.06
    ardino
    0.06
    æĸ°å®ī
    0.06
     hered
    0.05
    æµģæ°´
    0.05
    czyn
    0.05
    fully
    0.05
    fulness
    0.05
     ind
    0.05
    emos
    0.05
    Activations Density 0.001%

    No Known Activations