© 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. 20764
    Prev
    Next
    INDEX
    Explanations

    or

    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
    gro
    -0.06
    å¾Ī
    -0.05
     terms
    -0.05
    coop
    -0.05
    ye
    -0.05
    ace
    -0.05
    ä¸ĵ
    -0.05
     apos
    -0.05
    aç
    -0.05
    дение
    -0.05
    POSITIVE LOGITS
    涯
    0.06
    ä¸Ģæ¯Ķ
    0.06
    ãģŁãģ£ãģ¦
    0.06
    [][]
    0.06
    technolog
    0.06
    quir
    0.06
    oje
    0.06
    /about
    0.06
    àµį
    0.06
    gebn
    0.06
    Activations Density 0.118%

    No Known Activations