© 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. 20511
    Prev
    Next
    INDEX
    Explanations

    typeof.isDirectoryisArrayFunction

    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
    c
    -0.07
    str
    -0.06
    quest
    -0.05
    裾
    -0.05
    å¦Ĥæŀľåľ¨
    -0.05
    æ£
    -0.05
    ÑĢиз
    -0.05
    abb
    -0.05
    cv
    -0.05
    端çļĦ
    -0.05
    POSITIVE LOGITS
    ðŁĻĤ
    0.06
    LAM
    0.06
    kyat
    0.06
    人åıĹ伤
    0.05
    yip
    0.05
    bolt
    0.05
    raft
    0.05
    eing
    0.05
    LAY
    0.05
    ken
    0.05
    Activations Density 0.027%

    No Known Activations