© 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. 18645
    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
    äk
    -0.08
     exactly
    -0.07
     behalf
    -0.06
    tidig
    -0.06
    Exactly
    -0.06
    corre
    -0.06
     Exactly
    -0.06
    _CN
    -0.06
    DEX
    -0.06
     jed
    -0.06
    POSITIVE LOGITS
    0.06
    pipe
    0.05
    λει
    0.05
    åı£
    0.05
    -hash
    0.05
    retta
    0.05
    çĪ·
    0.05
    hip
    0.05
    aster
    0.05
    转åŀĭåıijå±ķ
    0.05
    Activations Density 0.006%

    No Known Activations