© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19471
    Prev
    Next
    INDEX
    Explanations

    loop or threads

    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
    umni
    -0.07
     Arro
    -0.07
    微信平åı°
    -0.07
    ordo
    -0.06
     asynchronously
    -0.06
    对äºİéĤ£äºĽ
    -0.06
    avera
    -0.06
    åıĬåħ¶èĩªåĬ¨åĮĸ
    -0.06
     ddl
    -0.06
    ä¸įéĢĤ
    -0.06
    POSITIVE LOGITS
     Handbook
    0.06
    amp
    0.05
    w
    0.05
     Forever
    0.05
    anted
    0.05
    it
    0.05
     Enc
    0.05
    éķ¿æľŁ
    0.05
    åīįæĻ¯
    0.05
    ampen
    0.05
    Activations Density 0.009%

    No Known Activations