© 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. 19828
    Prev
    Next
    INDEX
    Explanations

    I am a

    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
    oogle
    -0.06
    adura
    -0.05
    ubl
    -0.05
    éĥ¨åĪĨåĨħ容
    -0.05
    kannya
    -0.05
     Ment
    -0.05
    æľīçĶŁ
    -0.05
    uwd
    -0.05
    åĶ¾
    -0.05
    åIJ«ç¬ij
    -0.05
    POSITIVE LOGITS
    ache
    0.06
    èĭ¥æĺ¯
    0.06
    YPE
    0.06
    visto
    0.06
     sensit
    0.05
    lung
    0.05
    å¦Ĥæŀľæĺ¯
    0.05
    yre
    0.05
    low
    0.05
    opo
    0.05
    Activations Density 0.008%

    No Known Activations