© 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. 18933
    Prev
    Next
    INDEX
    Explanations

    neglect and negligence

    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
    verläss
    -0.07
    yki
    -0.07
    alnız
    -0.07
    åĩºä¸į
    -0.07
    yty
    -0.07
    å¼Ģ好
    -0.07
    agné
    -0.07
     Jinping
    -0.07
    peg
    -0.07
    åĸ°
    -0.06
    POSITIVE LOGITS
    0.06
     casually
    0.05
    4
    0.05
     reckless
    0.05
    çİ©
    0.05
     Co
    0.05
     Default
    0.04
    ↵↵
    0.04
    typ
    0.04
     Shared
    0.04
    Activations Density 0.007%

    No Known Activations