© 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. 19120
    Prev
    Next
    INDEX
    Explanations

    answer or response

    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
    ker
    -0.06
    æĿijåĨħ
    -0.06
    该款
    -0.05
    ç½ĹæĽ¼
    -0.05
     rel
    -0.05
    ington
    -0.05
    çļĦæĺ¯ä¸Ģ个
    -0.05
    -0.05
    éĺŁä¼įçļĦ
    -0.05
    çļĦçľ¼
    -0.05
    POSITIVE LOGITS
    解çŃĶ
    0.08
    ayakan
    0.06
    mada
    0.06
     Bosco
    0.05
    å½±
    0.05
    opard
    0.05
    ersp
    0.05
    orry
    0.05
    åĽŀçŃĶ
    0.05
    æī
    0.05
    Activations Density 0.019%

    No Known Activations