© 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. 19194
    Prev
    Next
    INDEX
    Explanations

    value assignment

    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
    æĪij们å°Ĩä¼ļ
    -0.06
    ingend
    -0.06
     worth
    -0.06
     Kidd
    -0.06
    upra
    -0.06
     retaining
    -0.06
    estin
    -0.05
    åĻ¨
    -0.05
     newfound
    -0.05
    leistung
    -0.05
    POSITIVE LOGITS
    ungan
    0.05
    æ²®
    0.05
    unis
    0.05
    침
    0.05
    воÑģ
    0.05
    èĦ±
    0.05
     fug
    0.05
    æݧ
    0.05
    æ»
    0.05
    ñas
    0.05
    Activations Density 0.031%

    No Known Activations