© 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. 17939
    Prev
    Next
    INDEX
    Explanations

    http headers:

    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
    er
    -0.05
    èĪĮ
    -0.05
    R
    -0.05
    çĪ
    -0.05
     switch
    -0.04
    pah
    -0.04
    ä¸į
    -0.04
     advocate
    -0.04
    沿çĿĢ
    -0.04
    秽
    -0.04
    POSITIVE LOGITS
    adar
    0.07
    ÑģÑĤил
    0.07
    زاÙĨ
    0.07
    onde
    0.07
    å®ĺæĸ¹åįļ客
    0.07
    arate
    0.07
    ondes
    0.07
    è¿ĶåĽŀåĪĹ表
    0.07
    ilter
    0.06
    ils
    0.06
    Activations Density 0.005%

    No Known Activations