© 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. 22574
    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
    Negative Logits
    enant
    -0.05
     diffuse
    -0.05
    chant
    -0.05
    ptica
    -0.05
    çģ«çĥ§
    -0.05
    acing
    -0.05
     اÙĦÙħاضÙĬØ©
    -0.05
    оÑģÑĥ
    -0.05
    åĴ³
    -0.05
    asper
    -0.05
    POSITIVE LOGITS
    iÄį
    0.06
    çļĦä¸ĵä¸ļ
    0.06
    缸è¿ij
    0.06
    icl
    0.05
    amy
    0.05
    ORTH
    0.05
    tl
    0.05
    ä¸ĵä¸ļ
    0.05
     elevado
    0.05
     Fondation
    0.05
    Activations Density 0.000%

    No Known Activations