© 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. 19483
    Prev
    Next
    INDEX
    Explanations

    latent factor analysis models

    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
     kata
    -0.07
    водÑĭ
    -0.06
    æĬµ
    -0.06
    å¹³åľ°
    -0.06
    åģ¥
    -0.06
    asp
    -0.05
    ä¸Ģæ¯Ķ
    -0.05
    cera
    -0.05
    ulet
    -0.05
    boek
    -0.05
    POSITIVE LOGITS
    ANTA
    0.06
    kund
    0.05
    iens
    0.05
    ä¸įæķ£
    0.05
    çŃīé¢Ĩ导
    0.05
    anta
    0.05
    es
    0.05
    ál
    0.05
    群
    0.05
    æħµæĩĴ
    0.05
    Activations Density 0.010%

    No Known Activations