© 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. 19859
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

    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
    orong
    -0.06
    éľ²å¤´
    -0.06
    éķ¿åº¦
    -0.06
    .Length
    -0.06
    =length
    -0.06
     libero
    -0.06
    itel
    -0.06
     Ristor
    -0.06
    ä¹ĸ
    -0.06
    æĿİåĺī
    -0.06
    POSITIVE LOGITS
    ätter
    0.05
    æĺĮ缼
    0.05
     consolid
    0.05
    ouis
    0.05
    ched
    0.05
    ro
    0.05
    æľīçĶŁ
    0.05
    éĩ
    0.05
    igner
    0.05
    prav
    0.05
    Activations Density 0.011%

    No Known Activations