© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21623
    Prev
    Next
    INDEX
    Explanations

    how can I

    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
    æľ¬èº«å°±
    -0.06
    еÑĤа
    -0.05
    æľ¬èº«å°±æĺ¯
    -0.05
     mén
    -0.05
    agos
    -0.05
    æĦıæĢĿæĺ¯
    -0.05
     именно
    -0.05
    inded
    -0.05
    ìĭľê¸¸
    -0.05
    zog
    -0.05
    POSITIVE LOGITS
    imd
    0.06
    滾
    0.06
    olly
    0.06
    artal
    0.06
    unker
    0.06
    use
    0.06
    æĵļ
    0.06
    å¦ĤèĬ±
    0.06
    çļĦåħ¨éĥ¨åĨħ容
    0.05
    ĵĴ
    0.05
    Activations Density 0.008%

    No Known Activations