© 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. 19103
    Prev
    Next
    INDEX
    Explanations

    .Alert Manufacturing Radio gel sheet superpower

    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
    èĤ²
    -0.05
    ен
    -0.05
    ÙĪØŃ
    -0.05
    ieh
    -0.05
     dimensional
    -0.05
     us
    -0.05
     Con
    -0.05
    æĻ®
    -0.05
     dimension
    -0.05
     Kon
    -0.04
    POSITIVE LOGITS
    ấu
    0.08
    akai
    0.07
    éĺĻ
    0.07
    æľĿéĺ³
    0.06
     comps
    0.06
    解åĨ³å®ŀéĻħ
    0.06
    reader
    0.06
    engi
    0.06
    ’S
    0.06
    ÑĢовна
    0.06
    Activations Density 0.198%

    No Known Activations