© 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. 18163
    Prev
    Next
    INDEX
    Explanations

    generated by a tool

    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
    essi
    -0.07
    xit
    -0.06
    ajo
    -0.06
    ouri
    -0.06
     Bond
    -0.06
    pag
    -0.06
    èģĶéĺ²
    -0.06
    大éĢļ
    -0.06
    建设ä¸İ
    -0.06
    signal
    -0.06
    POSITIVE LOGITS
    çĶŁæĪIJ
    0.06
    èĩªåĬ¨åĮĸ
    0.06
    éĢĶå¾Ħ
    0.05
     cib
    0.05
     generated
    0.05
     coverage
    0.05
    è¦ĨçĽĸéĿ¢
    0.05
     generate
    0.05
     partial
    0.05
     hammer
    0.05
    Activations Density 0.132%

    No Known Activations