© 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. 22131
    Prev
    Next
    INDEX
    Explanations

    relative

    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
     straight
    -0.06
    åľ¨è¡ĮåĬ¨
    -0.05
    ëŀĺ
    -0.05
    straight
    -0.05
    æĸ¯
    -0.05
    åīį人
    -0.05
    æĬķèµĦä»·åĢ¼
    -0.05
    odar
    -0.05
    å®ŀå¤Ħ
    -0.05
     v
    -0.05
    POSITIVE LOGITS
     Relative
    0.07
    Relative
    0.07
    universal
    0.06
     relative
    0.06
    -relative
    0.06
    iversal
    0.06
    Universal
    0.06
    çĽ¸å¯¹
    0.06
    relative
    0.06
     Universal
    0.06
    Activations Density 0.111%

    No Known Activations