© 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. 20945
    Prev
    Next
    INDEX
    Explanations

    may be outdated or vary

    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
    vern
    -0.07
     trÃŃ
    -0.06
    æ±Ĥæĺ¯
    -0.06
    urna
    -0.06
    spot
    -0.05
    adž
    -0.05
    entar
    -0.05
     Noticed
    -0.05
     Susp
    -0.05
    æĻºæħ§åŀĭ
    -0.05
    POSITIVE LOGITS
    acker
    0.06
    ä¸įä»ħå¦ĤæѤ
    0.05
    atitis
    0.05
     ìĪĻ
    0.05
    è§Ħå®ļçļĦ
    0.05
    refs
    0.05
    ัà¸Ļ
    0.05
    asnya
    0.05
    对éĤ£äºĽ
    0.05
    稳
    0.05
    Activations Density 0.012%

    No Known Activations