© 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. 21225
    Prev
    Next
    INDEX
    Explanations

    units or 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
    pose
    -0.07
    änger
    -0.06
    æĿ¥è¿ĩ
    -0.06
    maries
    -0.05
    ä¸Ģåıij
    -0.05
    ancies
    -0.05
    emos
    -0.05
    ninger
    -0.05
    azar
    -0.05
     nied
    -0.05
    POSITIVE LOGITS
    æŁ¥
    0.06
    åħĦ妹
    0.06
    æľīçļĦ
    0.05
    ä¹ĭæīĢ以
    0.05
    igne
    0.05
     gej
    0.05
     avrei
    0.05
     hindsight
    0.05
     Ñģб
    0.05
    æ®Ĭ
    0.05
    Activations Density 0.149%

    No Known Activations