© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22372
    Prev
    Next
    INDEX
    Explanations

    intersection of edges

    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
    Negative Logits
    icka
    -0.06
    çŃīç³»åĪĹ
    -0.06
    мÑıн
    -0.06
    amu
    -0.05
    åĬ©
    -0.05
    =com
    -0.05
    说è¯Ŀ
    -0.05
    åį¿
    -0.05
    SI
    -0.05
    äºĨ两个
    -0.05
    POSITIVE LOGITS
     overlapping
    0.08
     overlaps
    0.08
    Overlap
    0.07
     overlap
    0.07
    å¤ĩ
    0.06
    overlap
    0.06
     subset
    0.06
     maxim
    0.06
    Intersection
    0.05
     Intersection
    0.05
    Activations Density 0.053%

    No Known Activations