© 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. 19167
    Prev
    Next
    INDEX
    Explanations

    Lactobacillus, Thabo, Mark, Slipknot, sexual, Jag

    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
    y
    -0.05
    ç´¢
    -0.05
    åŁ
    -0.05
    γκ
    -0.05
     stuff
    -0.05
    raft
    -0.05
    ŀ
    -0.05
    社
    -0.05
    m
    -0.05
    U
    -0.05
    POSITIVE LOGITS
    IBUT
    0.07
     türl
    0.06
    èĭ±æĸĩåŃĹ
    0.06
    мÑĸнÑĸÑģÑĤÑĢа
    0.06
    бÑĥдÑĮÑĤе
    0.06
     disap
    0.06
    äºĨä¸Ģè·³
    0.06
    ?>>
    0.06
    /OR
    0.06
    ä½ĵå¼ı
    0.06
    Activations Density 0.050%

    No Known Activations