© 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. 18847
    Prev
    Next
    INDEX
    Explanations

    chemical structures and properties

    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
    kus
    -0.06
     ${(
    -0.06
    åĽŃæŀĹ绿åĮĸ
    -0.05
    fx
    -0.05
    si
    -0.05
    ä¸įå°½
    -0.05
    à¹Ģà¸Ĭืà¹īà¸Ń
    -0.05
    leys
    -0.05
     otr
    -0.05
    vo
    -0.05
    POSITIVE LOGITS
    åį³ä½¿åľ¨
    0.06
     collapse
    0.06
    伪
    0.05
     collapses
    0.05
    çĬ¶æĢģçļĦ
    0.05
    á»Ĵ
    0.05
    å¡ĮéĻ·
    0.05
    å¼±ãģĦ
    0.05
     Bonn
    0.05
    ä¹ĭä¸ĭçļĦ
    0.05
    Activations Density 0.025%

    No Known Activations