© 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. 20390
    Prev
    Next
    INDEX
    Explanations

    .string or property name definition

    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
    помина
    -0.05
     instead
    -0.05
    çªģçĦ¶
    -0.05
    åľ¨æѤ
    -0.05
    kie
    -0.05
     Gee
    -0.05
    å®ļä½į
    -0.05
    åİī害
    -0.05
    å·¦
    -0.04
    æĽ¿
    -0.04
    POSITIVE LOGITS
    adem
    0.06
    éĴ±äºĨ
    0.06
    ream
    0.06
    der
    0.06
     burge
    0.06
     Την
    0.05
    na
    0.05
    اÛĮØ´
    0.05
    cret
    0.05
    loss
    0.05
    Activations Density 0.003%

    No Known Activations