© 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. 18111
    Prev
    Next
    INDEX
    Explanations

    .org

    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
    DS
    -0.06
    fert
    -0.06
    æľīä¸Ģåıª
    -0.05
    åĮĢ
    -0.05
    itone
    -0.05
    èĬ·
    -0.05
    หล
    -0.05
    —one
    -0.05
    .live
    -0.05
    ÙĤÙĦت
    -0.05
    POSITIVE LOGITS
    elman
    0.06
    estaan
    0.06
    æ´²
    0.06
    çĬ¶
    0.06
     ì§ĵ
    0.06
     ÑģÑı
    0.06
    زÙĨØ©
    0.05
    å°¤æĸĩ
    0.05
    å¹²äºĭåĪĽä¸ļ
    0.05
    -options
    0.05
    Activations Density 0.002%

    No Known Activations