© 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. 20216
    Prev
    Next
    INDEX
    Explanations

    evaluation and measurement concepts

    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
    è°£
    -0.06
    olver
    -0.05
     spent
    -0.05
    sort
    -0.05
    æѤ类
    -0.05
    MENTS
    -0.05
     rop
    -0.05
    è¿Ļç±»
    -0.05
    åĪ¶æľį
    -0.05
    è°£è¨Ģ
    -0.05
    POSITIVE LOGITS
    idrat
    0.07
    ä½ĵ系建设
    0.07
    ä¸ĢåĪĩ
    0.07
     thirst
    0.06
    blig
    0.06
    ivosti
    0.06
    idon
    0.06
    áĢIJáĢº
    0.06
     Teil
    0.06
    åı£æ¸´
    0.06
    Activations Density 0.012%

    No Known Activations