© 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. 19425
    Prev
    Next
    INDEX
    Explanations

    important concerns

    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
    ovil
    -0.06
    Ú¯ÛĮ
    -0.06
    ÑĩкÑĥ
    -0.05
    bit
    -0.05
    å¾Ħ
    -0.05
    term
    -0.05
    _band
    -0.05
     дам
    -0.05
    agno
    -0.05
    iday
    -0.05
    POSITIVE LOGITS
    astre
    0.06
    izzo
    0.06
     strain
    0.06
    对ä»ĸçļĦ
    0.06
    %A
    0.05
    ÑģÑĤе
    0.05
    ä¸ĢéŨ
    0.05
     Studies
    0.05
    %B
    0.05
    åIJĪçIJĨåĮĸ
    0.05
    Activations Density 0.069%

    No Known Activations