© 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. 21389
    Prev
    Next
    INDEX
    Explanations

    lists of entities

    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
    igger
    -0.06
    è¹Ħ
    -0.06
    ouv
    -0.06
    å¹ķ
    -0.06
     dém
    -0.06
    interess
    -0.06
    ringer
    -0.06
     roy
    -0.06
    ä¸įèµ·æĿ¥
    -0.06
    çİĭçīĮ
    -0.05
    POSITIVE LOGITS
    еÑħа
    0.05
    éĩİ
    0.05
    ernel
    0.05
    室
    0.05
     l
    0.05
     cous
    0.05
    esor
    0.05
    а
    0.05
     initially
    0.05
     inherently
    0.05
    Activations Density 0.025%

    No Known Activations