© 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. 17042
    Prev
    Next
    INDEX
    Explanations

    explanation of terms

    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
     contained
    -0.05
    åĩı
    -0.05
    æĮª
    -0.05
    ori
    -0.05
    ä¸įæĿ¥
    -0.05
    ation
    -0.05
    гÑĸ
    -0.05
    yv
    -0.05
    ods
    -0.05
    age
    -0.04
    POSITIVE LOGITS
    ensif
    0.07
    ðŁĻĤ
    0.07
    licity
    0.06
    uong
    0.06
    atically
    0.06
    æĪijçľĭçĿĢ
    0.06
    variably
    0.06
    ensively
    0.06
    åı£åijĨ
    0.06
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.06
    Activations Density 0.005%

    No Known Activations