© 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. 20075
    Prev
    Next
    INDEX
    Explanations

    `.property $language`

    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
    æŶéĹ´éķ¿
    -0.05
     vá
    -0.05
    aisen
    -0.05
    ij
    -0.05
    æł¹æ·±
    -0.05
     (((
    -0.05
    æĦıèŃĺ
    -0.05
    æĥ¯äºĨ
    -0.05
    ä¿®éģĵ
    -0.05
    åij½ä»¤
    -0.05
    POSITIVE LOGITS
    Äıaka
    0.07
    ÐĵлавнÑĭе
    0.06
    å¿«æĿ¥
    0.06
    çĿĢåĬĽçĤ¹
    0.05
    ħĮ
    0.05
     particulars
    0.05
    åĽŃåľ°
    0.05
    æłijä¸Ģ
    0.05
    ere
    0.05
    jun
    0.05
    Activations Density 0.001%

    No Known Activations