© 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. 19133
    Prev
    Next
    INDEX
    Explanations

    API gateway bot configs

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ondo
    -0.06
    pret
    -0.06
     sections
    -0.05
    pr
    -0.05
    æĢ§è´¨çļĦ
    -0.05
    ä»·
    -0.05
    ToF
    -0.05
    aglia
    -0.05
    è·ijè·¯
    -0.05
    Directories
    -0.05
    POSITIVE LOGITS
    egr
    0.06
     reins
    0.06
    ready
    0.06
    ipan
    0.06
     $("#"
    0.06
     $('#'
    0.06
    ifo
    0.05
     shaping
    0.05
     ades
    0.05
    ÑĢева
    0.05
    Activations Density 0.002%

    No Known Activations