© 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. 21921
    Prev
    Next
    INDEX
    Explanations

    print output

    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
     ar
    -0.05
     intellectual
    -0.05
     standalone
    -0.05
     equivalents
    -0.05
    æ¦Ĥè¦ģ
    -0.05
     tu
    -0.05
    à¸Ļà¹īà¸Ńย
    -0.05
    wegs
    -0.05
     "
    -0.05
    ights
    -0.05
    POSITIVE LOGITS
    ÙĦÙĪÙĦ
    0.07
     intervening
    0.06
    probe
    0.06
    æѤæŶ
    0.06
     thereafter
    0.06
     subsequent
    0.06
    æѤæŶçļĦ
    0.06
    (after
    0.06
    à¹Ģà¸Ĭ
    0.06
    âĢ¦ãĢĤ
    0.06
    Activations Density 0.020%

    No Known Activations