© 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. 20737
    Prev
    Next
    INDEX
    Explanations

    regardless of whether

    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
    venuto
    -0.06
    ities
    -0.06
    olim
    -0.05
    oner
    -0.05
    å¸Ĥä¸Ń
    -0.05
     unary
    -0.05
    åĭ¢
    -0.05
    äºİä¸ĸ
    -0.05
    INGS
    -0.05
    åĽ½åĬ¡éĻ¢åħ³äºİ
    -0.05
    POSITIVE LOGITS
    åħ¶
    0.06
    ation
    0.06
    kert
    0.06
     léo
    0.06
    ett
    0.06
    ãģĦãģĨ
    0.06
    ally
    0.06
    ism
    0.06
    æĺ¯å®¢æĪ·
    0.06
    ØŃتÙĩا
    0.06
    Activations Density 0.004%

    No Known Activations