© 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. 21076
    Prev
    Next
    INDEX
    Explanations

    relationship between

    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
    个æĸ¹éĿ¢
    -0.06
    toral
    -0.06
    æ²³åĮº
    -0.06
    asai
    -0.06
    hcp
    -0.06
    ürnberg
    -0.06
    æľĭ
    -0.06
    èĩªçĶ±éĢīæĭ©
    -0.06
    à¸Ĭà¸Ļ
    -0.06
    å¦Ĥä½ķéĢīæĭ©
    -0.06
    POSITIVE LOGITS
     through
    0.06
    éĢļè¿ĩåIJİ
    0.06
    计
    0.06
     via
    0.05
     lewat
    0.05
    ç»ıè¿ĩ
    0.05
     thru
    0.05
     qua
    0.05
    via
    0.05
    éĢļè¿ĩ
    0.05
    Activations Density 0.013%

    No Known Activations