© 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. 20211
    Prev
    Next
    INDEX
    Explanations

    making a consequence of

    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
     Siap
    -0.05
    à¹ĩà¸Ķ
    -0.05
     continuum
    -0.05
    ç¡®ä¿Ŀå®īåħ¨
    -0.05
    åīį人
    -0.05
    综åIJĪ
    -0.05
    acam
    -0.05
     wouldn
    -0.05
     super
    -0.05
    yed
    -0.05
    POSITIVE LOGITS
    ÙĪاÙħ
    0.06
    ÙĴتÙİ
    0.06
    éł»
    0.06
    endir
    0.06
    åģļä»Ģä¹Ī
    0.06
    ä¸Ģç½ij
    0.06
    è¾ĥå¤ļçļĦ
    0.06
    ãĤ¹ãĥĪ
    0.06
     dirige
    0.06
    è¿ĩå¤ļçļĦ
    0.06
    Activations Density 0.024%

    No Known Activations