© 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. 18632
    Prev
    Next
    INDEX
    Explanations

    be

    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
    ä»Ģ
    -0.06
     emoc
    -0.05
    omod
    -0.05
    éĵģé¾Ļ
    -0.05
    datal
    -0.05
     ÑĤÑĢе
    -0.05
    innov
    -0.05
    uite
    -0.05
    owie
    -0.05
     inov
    -0.05
    POSITIVE LOGITS
    èĩªçĦ¶çļĦ
    0.07
     natural
    0.07
    çľŁå¯¦
    0.07
    èĩªçĦ¶
    0.06
     наÑĤÑĥÑĢалÑĮнÑĭй
    0.06
     Natural
    0.06
    羣å®ŀçļĦ
    0.06
     true
    0.06
     genuine
    0.06
    çļĦ羣å®ŀæĢ§
    0.06
    Activations Density 0.143%

    No Known Activations