© 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. 18261
    Prev
    Next
    INDEX
    Explanations

    question or choice

    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
    mond
    -0.05
    acz
    -0.05
    çļĦä¸ĸçķĮéĩĮ
    -0.05
    åıĹéĺ»
    -0.05
    éŃĶ
    -0.05
    ÈĻte
    -0.05
    Cir
    -0.05
    \u
    -0.05
     execu
    -0.05
    Ùĩ
    -0.05
    POSITIVE LOGITS
     ooit
    0.06
     Rape
    0.06
    berge
    0.06
     avg
    0.06
    avg
    0.05
     Cẩm
    0.05
    vai
    0.05
    å¤ĩ
    0.05
    gement
    0.05
    äºĮæľĪ
    0.05
    Activations Density 0.001%

    No Known Activations