© 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. 18906
    Prev
    Next
    INDEX
    Explanations

    of vascular, angiopathy, phenylalanine, a, the

    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
    agerie
    -0.07
    æ´»åĬ¨åľ¨
    -0.06
    é¡¹çĽ®åľ¨
    -0.06
    å¾·åįİ
    -0.06
    没帮åĬ©
    -0.06
     kupon
    -0.06
    perfil
    -0.06
    theless
    -0.06
     Lista
    -0.06
    马èĻİ
    -0.06
    POSITIVE LOGITS
    aska
    0.06
    æł¡
    0.05
     wanted
    0.05
    ç½²
    0.05
    åĦŁ
    0.05
     samples
    0.05
    ski
    0.05
     дол
    0.05
     based
    0.05
    veri
    0.04
    Activations Density 0.001%

    No Known Activations