© 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. 20051
    Prev
    Next
    INDEX
    Explanations

    pollination, pollen, bees

    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
    erview
    -0.07
     dispos
    -0.06
    heits
    -0.06
    æĦŁæŁĵèĢħ
    -0.06
    heit
    -0.06
    åħ¸åŀĭçļĦ
    -0.06
    å¤įåį°ä»¶
    -0.06
    æ·
    -0.06
     typing
    -0.06
    èľķ
    -0.06
    POSITIVE LOGITS
    nect
    0.07
     pollen
    0.06
    åĿĬ
    0.06
    roid
    0.06
    .Microsoft
    0.05
    airs
    0.05
    Reusable
    0.05
    dio
    0.05
    éľĵ
    0.05
    ä»ĻåŃIJ
    0.05
    Activations Density 0.011%

    No Known Activations