© 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
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17920
    Prev
    Next
    INDEX
    Explanations

    programming initialization calls

    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
    ogo
    -0.06
    çļ®ä¹¦
    -0.06
    ساÙĨÙĬØ©
    -0.06
    onta
    -0.06
    åŃ©
    -0.05
    Ĥ¬
    -0.05
    annis
    -0.05
    称
    -0.05
    éħ·
    -0.05
    çļ®çļĦ
    -0.05
    POSITIVE LOGITS
    cam
    0.06
    cient
    0.06
    zil
    0.05
    tent
    0.05
     lần
    0.05
    é¤IJ
    0.05
    羶
    0.05
    scientific
    0.05
    teil
    0.05
    ières
    0.05
    Activations Density 0.069%

    No Known Activations