© 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. 19216
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    emente
    -0.07
    ç»į
    -0.07
    estal
    -0.07
     beho
    -0.07
    urin
    -0.06
    wohl
    -0.06
    çļĦãģ«ãĤĤ
    -0.06
    mut
    -0.06
     getattr
    -0.06
     mattino
    -0.06
    POSITIVE LOGITS
    ä¸Ńä¹ĭ
    0.05
     last
    0.05
    ↵
    0.05
    åħľ
    0.05
     bu
    0.05
     misplaced
    0.05
     vs
    0.05
    伺
    0.05
    æ£
    0.04
    ä¸Ģåij³
    0.04
    Activations Density 0.003%

    No Known Activations