© 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. 20308
    Prev
    Next
    INDEX
    Explanations

    cleavage

    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
    -average
    -0.06
    ipheral
    -0.06
    whel
    -0.06
    Ø·ÙĪاÙĨ
    -0.06
    å¯Ħ
    -0.05
    iori
    -0.05
    èĢĮå°±
    -0.05
    æľĢä½İçļĦ
    -0.05
    çĺ¾
    -0.05
    æĹłåģ¿çĮ®è¡Ģ
    -0.05
    POSITIVE LOGITS
    summ
    0.06
    back
    0.06
    éħ¸ç¢±
    0.05
    endÅij
    0.05
    tanda
    0.05
    Ãło
    0.05
     Somerset
    0.05
    zet
    0.05
    ë©´
    0.05
    Appearance
    0.05
    Activations Density 0.001%

    No Known Activations