© 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. 18807
    Prev
    Next
    INDEX
    Explanations

    following a list of items

    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
    好
    -0.05
     list
    -0.05
    (
    -0.05
    å°¤åħ¶æĺ¯åľ¨
    -0.05
     multit
    -0.05
    æľīè¿ĩ
    -0.05
    æľī好
    -0.05
    æĺ¯ä¸Ģå¥Ĺ
    -0.05
    "
    -0.05
    ward
    -0.04
    POSITIVE LOGITS
    Siamo
    0.07
    полне
    0.07
    ucia
    0.07
    siamo
    0.07
    strar
    0.06
    asthan
    0.06
    atively
    0.06
    avÃŃa
    0.06
    moz
    0.06
    ={({
    0.06
    Activations Density 0.023%

    No Known Activations