© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20108
    Prev
    Next
    INDEX
    Explanations

    smooth, thick, quality

    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
    éħį
    -0.05
     Nose
    -0.05
    peri
    -0.05
    plan
    -0.05
    leter
    -0.05
    é¼»åŃIJ
    -0.05
    æı
    -0.05
     nose
    -0.05
    å¾·æīį
    -0.05
    æĸ°é«ĺ
    -0.05
    POSITIVE LOGITS
    天é¹ħ
    0.06
    erce
    0.06
    aver
    0.06
    èĢį
    0.06
    ergi
    0.06
    ê¸ī
    0.06
    antal
    0.06
    ych
    0.06
     consig
    0.06
    iri
    0.06
    Activations Density 0.005%

    No Known Activations