© 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. 19614
    Prev
    Next
    INDEX
    Explanations

    themselves or itself

    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
    angu
    -0.07
     Abilities
    -0.06
     abilities
    -0.06
    abilities
    -0.06
    ÑīеÑĤ
    -0.06
    æ³ķ
    -0.06
    å¢ĥ
    -0.05
    éĻ¤ä»¥
    -0.05
     пÑĢигод
    -0.05
    èŀį
    -0.05
    POSITIVE LOGITS
    åĭķåĬĽ
    0.06
    åĬ¨åĬĽ
    0.06
    utz
    0.05
    away
    0.05
    ixon
    0.05
    åİ»çľĭçľĭ
    0.05
     away
    0.05
     rumbo
    0.05
     اÙĦØŃÙĤÙĬÙĤÙĬ
    0.05
    èĢĮåİ»
    0.05
    Activations Density 0.005%

    No Known Activations