© 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. 20133
    Prev
    Next
    INDEX
    Explanations

    two independent pathways

    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
    plevel
    -0.06
    à¹Ĭะ
    -0.06
    以åıĬå¦Ĥä½ķ
    -0.06
     Worth
    -0.06
    ieti
    -0.06
     بتØŃ
    -0.06
    raph
    -0.06
    -AA
    -0.06
    odos
    -0.06
    ä¹Łæľª
    -0.06
    POSITIVE LOGITS
    usted
    0.06
    istr
    0.05
    ä¸į为
    0.05
    è¡£
    0.05
     non
    0.05
     crossing
    0.05
    itters
    0.05
    客çļĦ
    0.05
     Hemp
    0.05
     Eaton
    0.05
    Activations Density 0.012%

    No Known Activations