© 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. 19993
    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
    és
    -0.06
     aparent
    -0.05
    oretical
    -0.05
    ional
    -0.05
    3
    -0.05
    åħ¨æ°ij
    -0.05
    ism
    -0.05
    .Next
    -0.05
    è¿Ń
    -0.05
    åĪĿæŃ¥
    -0.04
    POSITIVE LOGITS
     richies
    0.08
    ectivo
    0.07
    brig
    0.07
     lesbi
    0.06
     Filoso
    0.06
    oen
    0.06
     fosser
    0.06
    onais
    0.06
    ìŀIJëĵ¤
    0.06
    ables
    0.06
    Activations Density 0.000%

    No Known Activations