© 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. 19275
    Prev
    Next
    INDEX
    Explanations

    specifies the following word

    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
    åİ»å¾Ģ
    -0.05
    ä¼ģä¸ļ管çIJĨåĴ¨è¯¢
    -0.05
     interfaces
    -0.05
    dak
    -0.05
    çĨŁçŁ¥
    -0.05
    olut
    -0.05
    åĮªæµħ
    -0.05
    é½IJé²ģ
    -0.05
    reserved
    -0.05
     balances
    -0.05
    POSITIVE LOGITS
    aghan
    0.06
    åľ¨åħ¶
    0.06
     whore
    0.06
    ä»İåħ¶
    0.06
    åľ¨å®ĥ
    0.06
    igna
    0.05
    wo
    0.05
     considéra
    0.05
    åħ¶äºº
    0.05
    ingly
    0.05
    Activations Density 0.060%

    No Known Activations