© 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. 18548
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
    åı¯æ¢¦
    -0.07
    /her
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    ally
    -0.06
    plats
    -0.06
    ¬ģ
    -0.06
    apat
    -0.06
    åľ°ãģ§
    -0.06
    åĮĸçī©
    -0.06
    夢幻
    -0.06
    POSITIVE LOGITS
    央
    0.06
     sophistication
    0.05
    omm
    0.05
    泡
    0.05
     Visual
    0.05
    çľī
    0.05
    anic
    0.05
    ราà¸Ĭà¸ģาร
    0.05
    çļĩ
    0.05
    ecd
    0.05
    Activations Density 0.006%

    No Known Activations