© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 21847
    Prev
    Next
    INDEX
    Explanations

    academic or technical terms

    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
    ansa
    -0.06
    omie
    -0.06
    aneo
    -0.05
    檻
    -0.05
     paio
    -0.05
    haw
    -0.05
     bấy
    -0.05
    ilÃł
    -0.05
    emax
    -0.05
    ä»İä¸Ģ个
    -0.05
    POSITIVE LOGITS
    istine
    0.07
    åħ´åĽ½
    0.06
    ç»ĵå°¾
    0.06
     capitale
    0.06
    macher
    0.06
    ÏĢι
    0.06
    endum
    0.05
    UNC
    0.05
    ends
    0.05
    ÑĨ
    0.05
    Activations Density 0.615%

    No Known Activations