© 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. 19532
    Prev
    Next
    INDEX
    Explanations

    foreign content

    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
    临åħ¶
    -0.07
    terer
    -0.07
    صÙĪص
    -0.06
    íݸ
    -0.06
    æĺ¯åIJĹ
    -0.06
    undu
    -0.06
    otte
    -0.06
    avic
    -0.06
    eceÄŁini
    -0.06
     pis
    -0.06
    POSITIVE LOGITS
    طر
    0.05
    lando
    0.05
    çķĻ
    0.05
    å°ıç»ĵ
    0.05
     impress
    0.05
    Äįek
    0.05
    åŀĭä¼ģä¸ļ
    0.05
    åĪĨå±Ĥ
    0.05
    Lean
    0.05
    æĢ§
    0.05
    Activations Density 0.150%

    No Known Activations