© 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. 18544
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    affe
    -0.06
    åĪĨä¸įæ¸ħ
    -0.06
    æĪijä¹Łä¸įçŁ¥éģĵ
    -0.06
    åı¯æĺ¯ä»ĸ
    -0.06
     PureComponent
    -0.06
     Orn
    -0.06
    ume
    -0.06
    ÑĦе
    -0.06
    åĽŀå½Ĵ
    -0.06
    ostro
    -0.06
    POSITIVE LOGITS
    wart
    0.06
    nder
    0.05
    yszer
    0.05
    丧èij¬
    0.05
     Snake
    0.05
    anc
    0.05
    æŃ¹
    0.05
    iais
    0.05
    åįĥåı¤
    0.05
    æĸĩ书
    0.05
    Activations Density 0.004%

    No Known Activations