© 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. 21923
    Prev
    Next
    INDEX
    Explanations

    programming code and special characters

    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
    Âł
    -0.07
    ä¸įçł´
    -0.07
     наÑģÑĤÑĥп
    -0.06
    ambilan
    -0.06
    accompagnement
    -0.06
    nalis
    -0.06
    NotAllowed
    -0.06
     zatr
    -0.06
    åħļå§Ķå§Ķåijĺ
    -0.06
    éĽĨä¸ŃéļĶ离
    -0.06
    POSITIVE LOGITS
    -var
    0.06
    ëĭĪëĭ¤
    0.05
    ö
    0.05
     sott
    0.05
    estan
    0.05
    åIJį
    0.05
    ãĤĭãģ®ãģĮ
    0.05
    æĸ¹æĸ¹éĿ¢
    0.05
    ì¥IJ
    0.05
     spazi
    0.05
    Activations Density 0.001%

    No Known Activations