© 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. 18750
    Prev
    Next
    INDEX
    Explanations

    ?

    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
    çħ§çĽ¸
    -0.06
    çļĦåIJį
    -0.06
    ably
    -0.06
    ingas
    -0.05
     (“
    -0.05
    tra
    -0.05
    nhem
    -0.05
    èģļ
    -0.05
    ÏģοÏį
    -0.05
    tric
    -0.05
    POSITIVE LOGITS
    æİī
    0.07
    æİīäºĨ
    0.06
    pus
    0.06
    roma
    0.06
     Morm
    0.06
     rass
    0.06
    ResponseStatus
    0.06
    kad
    0.05
    åıĸç¼Ķ
    0.05
    æħķå°¼
    0.05
    Activations Density 0.001%

    No Known Activations