© 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. 19649
    Prev
    Next
    INDEX
    Explanations

    description

    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
    rette
    -0.06
    éķ
    -0.06
     juste
    -0.06
    ணà¯įà®Łà¯ģ
    -0.06
    umba
    -0.05
    ogi
    -0.05
    endorf
    -0.05
     Om
    -0.05
     capital
    -0.05
    ucat
    -0.05
    POSITIVE LOGITS
    bas
    0.06
    ä¸ĬåĽ¾
    0.06
    ÑĢо
    0.06
    holds
    0.06
    fare
    0.05
    еÑģÑĤа
    0.05
    schlag
    0.05
     Rabu
    0.05
     Sache
    0.05
    ลำ
    0.05
    Activations Density 0.007%

    No Known Activations