© 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. 19056
    Prev
    Next
    INDEX
    Explanations

    flat

    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
    ׼×ķת
    -0.06
    andon
    -0.06
    Ñĭм
    -0.06
    mate
    -0.06
    ê°IJìĿĦ
    -0.06
    istensi
    -0.05
    bcm
    -0.05
    ãģĭãģĹ
    -0.05
    cerr
    -0.05
    -mouth
    -0.05
    POSITIVE LOGITS
    æł·çļĦ
    0.06
    æĮĩ
    0.06
    æĭ¼
    0.05
    avin
    0.05
    <'
    0.05
    æĮ
    0.05
    客
    0.05
    没æľī
    0.05
    rieg
    0.05
    çĶ¨æĪ·ä½¿çĶ¨
    0.05
    Activations Density 0.001%

    No Known Activations