© 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. 21460
    Prev
    Next
    INDEX
    Explanations

    `test`

    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
    çĥ¤é±¼
    -0.06
    ä¹IJçļĦ
    -0.06
     سÙĨ
    -0.06
    ucc
    -0.06
     ..."
    -0.06
    æ¸ħæĻ°åľ°
    -0.06
    cassert
    -0.06
    ortex
    -0.06
    ussy
    -0.06
    ç«ĭ
    -0.06
    POSITIVE LOGITS
    æĺĤ
    0.05
     va
    0.05
    çªĹ
    0.05
    witz
    0.05
    ç»ķ
    0.05
     overrides
    0.05
    éľĢè¦ģä»İ
    0.05
     fo
    0.05
    ising
    0.05
    ำ
    0.05
    Activations Density 0.178%

    No Known Activations