© 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. 18547
    Prev
    Next
    INDEX
    Explanations

    type, input, bool, int, command

    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
    ,idx
    -0.06
    ocar
    -0.06
     życ
    -0.05
    fy
    -0.05
    fu
    -0.05
     comunque
    -0.05
    å¯ĵ
    -0.05
    anas
    -0.05
    客æĪ·æľįåĬ¡
    -0.05
     spro
    -0.05
    POSITIVE LOGITS
    лага
    0.06
    ÑģÑĤÑĢ
    0.06
    éĵĽ
    0.06
    arching
    0.05
    ладелÑĮ
    0.05
    ccd
    0.05
     str
    0.05
    ä¹ĭ称
    0.05
    ardin
    0.05
    çľĭåĪ°çļĦæĺ¯
    0.05
    Activations Density 0.005%

    No Known Activations