© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19531
    Prev
    Next
    INDEX
    Explanations

    its own

    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
    lej
    -0.06
    zhou
    -0.06
    scheid
    -0.05
    人èĥ½
    -0.05
    irro
    -0.05
    ãģ§ãģĹãģŁãģŃ
    -0.05
    imat
    -0.05
    ãĤ«ãĥł
    -0.05
    га
    -0.05
    á»įt
    -0.05
    POSITIVE LOGITS
    à¸ķà¹Ī
    0.07
    perhaps
    0.06
    .Properties
    0.06
     perhaps
    0.06
    å¾Ĺèµ·
    0.06
    aybe
    0.06
    åĪ«çļĦ
    0.06
    æĪĸ许æĺ¯
    0.06
    uw
    0.05
    ÑĨен
    0.05
    Activations Density 0.004%

    No Known Activations