© 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. 18353
    Prev
    Next
    INDEX
    Explanations

    numbers and names

    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
    볨
    -0.06
    à¸Ľà¸£à¸°
    -0.06
     mess
    -0.06
    éĩĩ
    -0.06
    inch
    -0.05
    verg
    -0.05
    ammel
    -0.05
     servis
    -0.05
    go
    -0.05
     Assembly
    -0.05
    POSITIVE LOGITS
     pura
    0.06
    اÙĨÙĬØ©
    0.06
    Ãŀ
    0.06
    太å¤ļ
    0.05
    åĩ¯å°Ķçī¹
    0.05
    ä¸Ńåŀĭ
    0.05
    TH
    0.05
    åĴ±
    0.05
    ë§Į
    0.05
    DEX
    0.05
    Activations Density 0.003%

    No Known Activations