© 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. 18723
    Prev
    Next
    INDEX
    Explanations

    Slug

    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
    dej
    -0.07
    ój
    -0.06
    aring
    -0.05
    ÄĻg
    -0.05
    è§Ħ磩
    -0.05
    çŁŃè¯Ń
    -0.05
    оÑĩ
    -0.05
    ients
    -0.05
    stood
    -0.05
    åħ³ç³»
    -0.05
    POSITIVE LOGITS
    olocation
    0.06
    ÙĪز
    0.06
    å¿ĥå¿ĥ
    0.06
    zilla
    0.06
    ske
    0.05
     ÙħÙĪا
    0.05
    ä¸ĭè¾ĸ
    0.05
    çļĦåķĬ
    0.05
    ØŃÙħ
    0.05
    uus
    0.05
    Activations Density 0.027%

    No Known Activations