© 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. 20352
    Prev
    Next
    INDEX
    Explanations

    three [items/categories]

    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
     flott
    -0.06
    raith
    -0.06
    доб
    -0.06
    eries
    -0.06
    ifer
    -0.06
    resse
    -0.06
    ä¸Ģæīĭ
    -0.06
     tú
    -0.06
    æĪĸ对
    -0.06
    loge
    -0.06
    POSITIVE LOGITS
    uel
    0.07
    æĺł
    0.05
    3
    0.05
    earth
    0.05
    ç¥
    0.05
    udo
    0.05
    管åĪ¶
    0.05
     Dodatkowo
    0.05
     proposons
    0.05
    åľ°
    0.05
    Activations Density 0.117%

    No Known Activations