© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19605
    Prev
    Next
    INDEX
    Explanations

    CRM Solutions Production

    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
    å±ħåīį
    -0.07
    izards
    -0.07
     constat
    -0.06
    æŀĦæĪIJçĬ¯ç½ªçļĦ
    -0.06
    laughter
    -0.06
     gián
    -0.06
    emark
    -0.06
    aderno
    -0.06
    uzzle
    -0.06
    æķĻè®Ń
    -0.06
    POSITIVE LOGITS
    udd
    0.06
    对åºĶçļĦ
    0.05
    æľīè¯Ŀ
    0.05
    ç¹ģ
    0.05
     subt
    0.05
    åħ¨
    0.05
    å¿ħçĦ¶
    0.05
    odz
    0.05
    ety
    0.05
    åĨħ容çļĦ
    0.05
    Activations Density 0.003%

    No Known Activations