© 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. 20383
    Prev
    Next
    INDEX
    Explanations

    education and career

    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
    çĶŁ
    -0.06
     dynamics
    -0.05
     пÑĢ
    -0.05
    tre
    -0.05
    بعاد
    -0.05
    c
    -0.05
    ç³Ļ
    -0.05
    ↵
    -0.05
    èī¯
    -0.05
     pr
    -0.05
    POSITIVE LOGITS
     ()->
    0.06
    éľ²æ°´
    0.06
    icter
    0.06
    variably
    0.06
    orte
    0.06
     trĩ
    0.06
    ukk
    0.06
    agl
    0.06
     Ñĥк
    0.06
    foro
    0.06
    Activations Density 0.016%

    No Known Activations